---
title: "Mac Studio M5 Ultra: What AI Models Can It Run? | ModelPiper"
description: "Local AI on the M5 Ultra Mac Studio: 1228 GB/s memory bandwidth and 96 to 512 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run."
canonical: "https://modelpiper.com/mac-studio/m5-ultra"
---

# Mac Studio M5 Ultra: What AI Models Can It Run? | ModelPiper

> Local AI on the M5 Ultra Mac Studio: 1228 GB/s memory bandwidth and 96 to 512 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run.

[← All Mac Studio models](/mac-studio)

# Mac Studio M5 Ultra

The M5 Ultra Mac Studio runs local models at 1228 GB/s of memory bandwidth with 96 to 512 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 512 GB you can hold roughly a 696B dense model at Q4. Two Max dies fused together: the widest memory bus and the highest capacity Apple sells. This is the tier that runs frontier-size open weights locally.

By [Ben Racicot](/about#founder), Founder & Lead Engineer— Updated 2026-08-21

## Specifications

ChipApple M5 Ultra

CPU cores30 or 36

GPU cores64 or 80

Unified memory96, 256, or 512 GB

Memory bandwidth1228 GB/s

Neural Engine76 TOPS

Released2026

AvailabilitySold new by Apple

Memory bandwidth is faster than 95% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 90% of them, against a 512 GB peak.

## Pick your configuration

Every option Apple sells with this chip. The model list below recomputes against the one you pick.

GPU cores

64-core 80-core

Unified memory

96 GB

Apple couples memory to the core count on this chip, so the options change with the bin above.

## What each memory option runs

Unified memory is the ceiling and it is soldered, so this is the decision you cannot revisit.

[96 GB](#ram-96gb)[256 GB](#ram-256gb)[512 GB](#ram-512gb)

### 96 GB unified memory

84 GB usable for weights · 1228 GB/s

6,384 of 6,563 models fit, and 6,271 of them run with headroom rather than as a squeeze.

Largest model at Q4

[LING 3.0 FLASH ABLITERATED](/fit/blackfrost-research-ling-3-0-flash-abliterated) · 127.49B

Best all-round pick

[Ornith 1.0 35B](/fit/deepreinforce-ai-ornith-1-0-35b) · Q8\_0 · ~236 tok/s

### 256 GB unified memory

225 GB usable for weights · 1228 GB/s

6,493 of 6,563 models fit, and 6,424 of them run with headroom rather than as a squeeze.

Largest model at Q4

[DeepSeek V3.2 REAP 345B A37B](/fit/cerebras-deepseek-v3-2-reap-345b-a37b) · 344.89B

Best all-round pick

[Ornith 1.0 35B](/fit/deepreinforce-ai-ornith-1-0-35b) · Q8\_0 · ~236 tok/s

### 512 GB unified memory

450 GB usable for weights · 1228 GB/s

6,549 of 6,563 models fit, and 6,490 of them run with headroom rather than as a squeeze.

Largest model at Q4

[A.X K2](/fit/skt-a-x-k2) · 691.69B

Best all-round pick

[Ornith 1.0 35B](/fit/deepreinforce-ai-ornith-1-0-35b) · Q8\_0 · ~236 tok/s

## What a 96 GB M5 Ultra Mac Studio can run

Every model in the database against this exact configuration, at 1228 GB/s. Ratings and speeds are the same numbers the model pages show.

All Categories

Show All

All Sizes

 Best Fit

Showing 6563 of 6563 models

[Ornith 1.0 35B](/fit/deepreinforce-ai-ornith-1-0-35b?chip=m5-ultra&ram=96)

General · deepreinforce-ai · 2026-06-21

Q8\_0Excellent

38.6 GB40% of RAMBenchmark needed34.13B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Ornith 1.0 9B](/fit/deepreinforce-ai-ornith-1-0-9b?chip=m5-ultra&ram=96)

General · deepreinforce-ai · 2026-06-21

Q8\_0Excellent

9.7 GB10% of RAM~78 tok/sEstimated8.21B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Kimi K3 DSpark](/fit/radixark-kimi-k3-dspark?chip=m5-ultra&ram=96)

General · radixark · 2026-07-27

Q8\_0Excellent

3.0 GB3% of RAM~286 tok/sEstimated2.25B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.6 35B A3B abliterated v4](/fit/bahushruth-qwen3-6-35b-a3b-abliterated-v4?chip=m5-ultra&ram=96)

General · bahushruth · 2026-06-11

Q8\_0Excellent

39.2 GB41% of RAMBenchmark needed34.66B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b?chip=m5-ultra&ram=96)

General · openbmb · 2026-05-21

Q8\_0Excellent

1.7 GB2% of RAM~596 tok/sEstimated1.08B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[OTel LLM 8B A1B IT](/fit/farbodtavakkoli-otel-llm-8b-a1b-it?chip=m5-ultra&ram=96)

General · farbodtavakkoli · 2026-06-17

Q8\_0Excellent

10.8 GB11% of RAMBenchmark needed9.23B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Agents A1 4B](/fit/internscience-agents-a1-4b?chip=m5-ultra&ram=96)

General · internscience · 2026-07-13

Q8\_0Excellent

5.6 GB6% of RAM~142 tok/sEstimated4.54B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 8B A1B](/fit/liquidai-lfm2-5-8b-a1b?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-05-28

Q8\_0Excellent

9.9 GB10% of RAMBenchmark needed8.47B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[automotive](/fit/flywheel-ai-automotive?chip=m5-ultra&ram=96)

General · flywheel-ai · 2026-06-21

Q8\_0Excellent

39.2 GB41% of RAMBenchmark needed34.66B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[VibeThinker 3B](/fit/weiboai-vibethinker-3b?chip=m5-ultra&ram=96)

General · weiboai · 2026-06-12

Q8\_0Excellent

3.9 GB4% of RAM~208 tok/sEstimated3.09B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 2.6B](/fit/liquidai-lfm2-5-2-6b?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-07-28

Q8\_0Excellent

3.5 GB4% of RAM~238 tok/sEstimated2.7B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen AgentWorld 35B A3B](/fit/qwen-qwen-agentworld-35b-a3b?chip=m5-ultra&ram=96)

General · Alibaba · 2026-06-22

Q8\_0Excellent

39.2 GB41% of RAMBenchmark needed34.66B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Laguna XS 2.1](/fit/poolside-laguna-xs-2-1?chip=m5-ultra&ram=96)

General · poolside · 2026-06-20

Q8\_0Excellent

37.8 GB39% of RAMBenchmark needed33.44B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 230M](/fit/liquidai-lfm2-5-230m?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-06-24

Q8\_0Excellent

0.8 GB1% of RAM~2,797 tok/sEstimated0.23B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Nanbeige4.2 3B](/fit/nanbeige-nanbeige4-2-3b?chip=m5-ultra&ram=96)

General · nanbeige · 2026-07-21

Q8\_0Excellent

5.2 GB5% of RAM~154 tok/sEstimated4.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwythos 9B Claude Mythos 5 1M](/fit/empero-ai-qwythos-9b-claude-mythos-5-1m?chip=m5-ultra&ram=96)

General · empero-ai · 2026-06-19

Q8\_0Excellent

11.0 GB11% of RAM~68 tok/sEstimated9.41B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.8\_4B\_Distilled\_GGUF](/fit/ma7ee7-qwen3-8_4b_distilled_gguf?chip=m5-ultra&ram=96)

General · ma7ee7 · 2026-07-30

Q8\_0Excellent

4.0 GB4% of RAM~206 tok/sEstimated3.13B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Apodex 1.0 mini](/fit/apodex-apodex-1-0-mini?chip=m5-ultra&ram=96)

General · apodex · 2026-06-07

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Agents A1](/fit/internscience-agents-a1?chip=m5-ultra&ram=96)

General · internscience · 2026-06-22

Q8\_0Excellent

39.7 GB41% of RAMBenchmark needed35.11B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[North Mini Code 1.0](/fit/coherelabs-north-mini-code-1-0?chip=m5-ultra&ram=96)

Coding · coherelabs · 2026-06-05

Q8\_0Excellent

34.5 GB36% of RAMBenchmark needed30.48B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[JOSIE 2 2B OSS](/fit/goekdeniz-guelmez-josie-2-2b-oss?chip=m5-ultra&ram=96)

General · goekdeniz-guelmez · 2026-07-31

Q8\_0Excellent

3.0 GB3% of RAM~283 tok/sEstimated2.27B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[JOSIE 2 9B OSS](/fit/goekdeniz-guelmez-josie-2-9b-oss?chip=m5-ultra&ram=96)

General · goekdeniz-guelmez · 2026-07-31

Q8\_0Excellent

11.3 GB12% of RAM~67 tok/sEstimated9.65B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[minicpm5 1b hermes toolhv1](/fit/ktruestory-minicpm5-1b-hermes-toolhv1?chip=m5-ultra&ram=96)

General · ktruestory · 2026-05-28

Q8\_0Excellent

1.7 GB2% of RAM~596 tok/sEstimated1.08B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[FrankenCPM 4x1B A2B](/fit/petrouil-frankencpm-4x1b-a2b?chip=m5-ultra&ram=96)

General · petrouil · 2026-07-23

Q8\_0Excellent

3.4 GB4% of RAMBenchmark needed2.61B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.6 35B A3B](/fit/qwen-qwen3-6-35b-a3b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-04-15

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.1 8b](/fit/ibm-granite-granite-4-1-8b?chip=m5-ultra&ram=96)

General · ibm-granite · 2026-04-06

Q8\_0Excellent

10.3 GB11% of RAM~73 tok/sEstimated8.79B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 12b it](/fit/google-gemma-4-12b-it?chip=m5-ultra&ram=96)

Multimodal · google · 2026-05

Q8\_0Excellent

13.8 GB14% of RAM~54 tok/sEstimated11.96B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.1 3b](/fit/ibm-granite-granite-4-1-3b?chip=m5-ultra&ram=96)

General · ibm-granite · 2026-04-06

Q8\_0Excellent

4.3 GB4% of RAM~189 tok/sEstimated3.4B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2](/fit/yuxinlu1-gemma-4-12b-agentic-fable5-composer2-5-v2-3-5x-tau2?chip=m5-ultra&ram=96)

General · yuxinlu1 · 2026-06-28

Q8\_0Excellent

13.8 GB14% of RAM~54 tok/sEstimated11.96B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite vision 4.1 4b](/fit/ibm-granite-granite-vision-4-1-4b?chip=m5-ultra&ram=96)

Multimodal · ibm-granite · 2026-04-16

Q8\_0Excellent

5.0 GB5% of RAM~161 tok/sEstimated4B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 350M](/fit/liquidai-lfm2-5-350m?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-03-31

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite guardian 4.1 8b](/fit/ibm-granite-granite-guardian-4-1-8b?chip=m5-ultra&ram=96)

General · ibm-granite · 2026-04-16

Q8\_0Excellent

9.8 GB10% of RAM~77 tok/sEstimated8.38B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[dspv2\_guide](/fit/lukebailey181pub-dspv2_guide?chip=m5-ultra&ram=96)

General · lukebailey181pub · 2026-04-21

Q8\_0Excellent

8.2 GB9% of RAM~93 tok/sEstimated6.91B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 26B A4B it uncensored](/fit/trevorjs-gemma-4-26b-a4b-it-uncensored?chip=m5-ultra&ram=96)

General · trevorjs · 2026-04-03

Q8\_0Excellent

29.3 GB31% of RAMBenchmark needed25.81B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Laguna XS.2](/fit/poolside-laguna-xs-2?chip=m5-ultra&ram=96)

General · poolside · 2026-04-23

Q8\_0Excellent

37.8 GB39% of RAMBenchmark needed33.44B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Gemma 4 12B OBLITERATED](/fit/obliteratus-gemma-4-12b-obliterated?chip=m5-ultra&ram=96)

General · obliteratus · 2026-06-05

Q8\_0Excellent

13.8 GB14% of RAM~54 tok/sEstimated11.96B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Huihui gemma 4 12B agentic fable5 abliterated](/fit/huihui-ai-huihui-gemma-4-12b-agentic-fable5-abliterated?chip=m5-ultra&ram=96)

General · huihui-ai · 2026-07-11

Q8\_0Excellent

13.8 GB14% of RAM~54 tok/sEstimated11.96B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 E4B it OBLITERATED](/fit/obliteratus-gemma-4-e4b-it-obliterated?chip=m5-ultra&ram=96)

General · obliteratus · 2026-04-15

Q8\_0Excellent

9.4 GB10% of RAM~80 tok/sEstimated8B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Huihui Qwen3.6 35B A3B Claude 4.7 Opus abliterated](/fit/huihui-ai-huihui-qwen3-6-35b-a3b-claude-4-7-opus-abliterated?chip=m5-ultra&ram=96)

General · huihui-ai · 2026-04-21

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Huihui Qwen3.6 35B A3B abliterated](/fit/huihui-ai-huihui-qwen3-6-35b-a3b-abliterated?chip=m5-ultra&ram=96)

Multimodal · huihui-ai · 2026-04-18

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 9B](/fit/qwen-qwen3-5-9b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

11.3 GB12% of RAM~67 tok/sEstimated9.65B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 26B A4B it](/fit/google-gemma-4-26b-a4b-it?chip=m5-ultra&ram=96)

Multimodal · Google · 2026-03-11

Q8\_0Excellent

30.1 GB31% of RAMBenchmark needed26.54B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 4B](/fit/qwen-qwen3-5-4b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

5.7 GB6% of RAM~138 tok/sEstimated4.66B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 E4B it](/fit/google-gemma-4-e4b-it?chip=m5-ultra&ram=96)

Multimodal · Google · 2026-03-02

Q8\_0Excellent

9.4 GB10% of RAM~80 tok/sEstimated8B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 4 E2B it](/fit/google-gemma-4-e2b-it?chip=m5-ultra&ram=96)

Multimodal · Google · 2026-03-02

Q8\_0Excellent

6.2 GB6% of RAM~126 tok/sEstimated5.12B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB2% of RAM~739 tok/sEstimated0.87B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 2B](/fit/qwen-qwen3-5-2b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB3% of RAM~283 tok/sEstimated2.27B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 35B A3B](/fit/qwen-qwen3-5-35b-a3b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-24

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 0.8B Base](/fit/qwen-qwen3-5-0-8b-base?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB2% of RAM~739 tok/sEstimated0.87B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 2B Base](/fit/qwen-qwen3-5-2b-base?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB3% of RAM~283 tok/sEstimated2.27B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 9B Base](/fit/qwen-qwen3-5-9b-base?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-26

Q8\_0Excellent

11.3 GB12% of RAM~67 tok/sEstimated9.65B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 4B Base](/fit/qwen-qwen3-5-4b-base?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

5.7 GB6% of RAM~138 tok/sEstimated4.66B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Nemotron Labs Diffusion 8B](/fit/nvidia-nemotron-labs-diffusion-8b?chip=m5-ultra&ram=96)

General · nvidia · 2026-03-18

Q8\_0Excellent

10.0 GB10% of RAM~76 tok/sEstimated8.49B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Dolphin3 Cyber 8B](/fit/ravichandranj-dolphin3-cyber-8b-gguf?chip=m5-ultra&ram=96)

General · ravichandranj · 2026-02-13

Q8\_0Excellent

7.7 GB8% of RAM~100 tok/sEstimated6.43B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Nemotron Cascade 2 30B A3B](/fit/nvidia-nemotron-cascade-2-30b-a3b?chip=m5-ultra&ram=96)

General · nvidia · 2026-03-18

Q8\_0Excellent

35.7 GB37% of RAMBenchmark needed31.58B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[sarvam 30b](/fit/sarvamai-sarvam-30b?chip=m5-ultra&ram=96)

General · sarvamai · 2026-03-03

Q8\_0Excellent

36.4 GB38% of RAMBenchmark needed32.15B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Nemotron Labs Diffusion 3B](/fit/nvidia-nemotron-labs-diffusion-3b?chip=m5-ultra&ram=96)

General · nvidia · 2026-03-02

Q8\_0Excellent

4.8 GB5% of RAM~168 tok/sEstimated3.83B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 24B A2B](/fit/liquidai-lfm2-24b-a2b?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-02-24

Q8\_0Excellent

27.1 GB28% of RAMBenchmark needed23.84B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled v2](/fit/jackrong-qwen3-5-9b-claude-4-6-opus-reasoning-distilled-v2?chip=m5-ultra&ram=96)

Reasoning · jackrong · 2026-03-16

Q8\_0Excellent

11.3 GB12% of RAM~67 tok/sEstimated9.65B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 35B A3B Claude 4.6 Opus Reasoning Distilled](/fit/jackrong-qwen3-5-35b-a3b-claude-4-6-opus-reasoning-distilled?chip=m5-ultra&ram=96)

Reasoning · jackrong · 2026-03-07

Q8\_0Excellent

40.6 GB42% of RAMBenchmark needed35.95B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[pii guard turkish 270m](/fit/cagrigungor-pii-guard-turkish-270m?chip=m5-ultra&ram=96)

General · cagrigungor · 2026-08-06

Q8\_0Excellent

0.8 GB1% of RAM~2,382 tok/sEstimated0.27B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[GLM 4.7 Flash](/fit/zai-org-glm-4-7-flash?chip=m5-ultra&ram=96)

General · zai-org · 2026-01-19

Q8\_0Excellent

35.3 GB37% of RAMBenchmark needed31.22B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 VL 1.6B](/fit/liquidai-lfm2-5-vl-1-6b?chip=m5-ultra&ram=96)

Multimodal · Liquid AI · 2026-01-05

Q8\_0Excellent

2.3 GB2% of RAM~402 tok/sEstimated1.6B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 1.2B Thinking](/fit/liquidai-lfm2-5-1-2b-thinking?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-01-20

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 3 12b it heretic](/fit/dreamfast-gemma-3-12b-it-heretic?chip=m5-ultra&ram=96)

General · dreamfast · 2026-01-11

Q8\_0Excellent

14.1 GB15% of RAM~53 tok/sEstimated12.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[AI21 Jamba2 3B](/fit/ai21labs-ai21-jamba2-3b?chip=m5-ultra&ram=96)

General · ai21labs · 2026-01-06

Q8\_0Excellent

3.9 GB4% of RAMBenchmark needed3.03B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Llama 3.1 8B Instruct pearl](/fit/pearl-ai-llama-3-1-8b-instruct-pearl?chip=m5-ultra&ram=96)

Chat · pearl-ai · 2026-02-26

Q8\_0Excellent

9.5 GB10% of RAM~80 tok/sEstimated8.03B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[OneReason 0.8B pretrain competition](/fit/openonerec-onereason-0-8b-pretrain-competition?chip=m5-ultra&ram=96)

Reasoning · openonerec · 2026-06-09

Q8\_0Excellent

1.4 GB1% of RAM~804 tok/sEstimated0.8B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 1.2B Base](/fit/liquidai-lfm2-5-1-2b-base?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-01-05

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 1.2B JP](/fit/liquidai-lfm2-5-1-2b-jp?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-01-04

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 2.6B Exp](/fit/liquidai-lfm2-2-6b-exp?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-12-25

Q8\_0Excellent

3.4 GB4% of RAM~250 tok/sEstimated2.57B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 2.6B Transcript](/fit/liquidai-lfm2-2-6b-transcript?chip=m5-ultra&ram=96)

General · Liquid AI · 2026-01-05

Q8\_0Excellent

3.4 GB4% of RAM~250 tok/sEstimated2.57B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Gemma 3 4B VL it Gemini Pro Heretic Uncensored Thinking](/fit/davidau-gemma-3-4b-vl-it-gemini-pro-heretic-uncensored-thinking?chip=m5-ultra&ram=96)

Multimodal · davidau · 2026-02-02

Q8\_0Excellent

5.3 GB6% of RAM~150 tok/sEstimated4.3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LaSER Qwen3 8B](/fit/alibaba-nlp-laser-qwen3-8b?chip=m5-ultra&ram=96)

General · alibaba-nlp · 2026-03-31

Q8\_0Excellent

9.6 GB10% of RAM~79 tok/sEstimated8.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2.5 1.2B Instruct](/fit/liquidai-lfm2-5-1-2b-instruct?chip=m5-ultra&ram=96)

Chat · Liquid AI · 2026-01-06

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[lynx instruct 30b](/fit/bineric-lynx-instruct-30b?chip=m5-ultra&ram=96)

Chat · bineric · 2026-01-12

Q8\_0Excellent

34.6 GB36% of RAMBenchmark needed30.53B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LLaDA2.1 mini](/fit/inclusionai-llada2-1-mini?chip=m5-ultra&ram=96)

General · inclusionai · 2026-02-09

Q8\_0Excellent

18.6 GB19% of RAMBenchmark needed16.26B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[TimeOmni 1 7B](/fit/anton-hugging-timeomni-1-7b?chip=m5-ultra&ram=96)

General · anton-hugging · 2026-02-06

Q8\_0Excellent

9.0 GB9% of RAM~84 tok/sEstimated7.62B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 ColBERT 350M](/fit/liquidai-lfm2-colbert-350m?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-10-28

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Olmo 3 7B Think](/fit/allenai-olmo-3-7b-think?chip=m5-ultra&ram=96)

General · allenai · 2025-11-18

Q8\_0Excellent

8.6 GB9% of RAM~88 tok/sEstimated7.3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 8B A1B](/fit/liquidai-lfm2-8b-a1b?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-10-07

Q8\_0Excellent

9.8 GB10% of RAMBenchmark needed8.34B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Olmo Hybrid 7B](/fit/allenai-olmo-hybrid-7b?chip=m5-ultra&ram=96)

General · allenai · 2026-01-28

Q8\_0Excellent

8.8 GB9% of RAM~87 tok/sEstimated7.43B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 VL 3B](/fit/liquidai-lfm2-vl-3b?chip=m5-ultra&ram=96)

Multimodal · Liquid AI · 2025-10-22

Q8\_0Excellent

3.8 GB4% of RAM~214 tok/sEstimated3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Lumma 0.6B Extract](/fit/frontiersmind-lumma-0-6b-extract?chip=m5-ultra&ram=96)

General · frontiersmind · 2026-08-03

Q8\_0Excellent

1.2 GB1% of RAM~990 tok/sEstimated0.65B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gpt oss 20b](/fit/openai-gpt-oss-20b?chip=m5-ultra&ram=96)

General · openai · 2025-08-04

Q8\_0Excellent

24.5 GB26% of RAMBenchmark needed21.51B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3 Coder 30B A3B Instruct](/fit/qwen-qwen3-coder-30b-a3b-instruct?chip=m5-ultra&ram=96)

Coding · Alibaba · 2025-07-31

Q8\_0Excellent

34.6 GB36% of RAMBenchmark needed30.53B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[typhoon2.5 qwen3 4b](/fit/typhoon-ai-typhoon2-5-qwen3-4b?chip=m5-ultra&ram=96)

General · typhoon-ai · 2025-09-23

Q8\_0Excellent

5.0 GB5% of RAM~160 tok/sEstimated4.02B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[T lite it 2.1](/fit/t-tech-t-lite-it-2-1?chip=m5-ultra&ram=96)

General · t-tech · 2025-12-22

Q8\_0Excellent

9.6 GB10% of RAM~79 tok/sEstimated8.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3 4B Thinking 2507](/fit/qwen-qwen3-4b-thinking-2507?chip=m5-ultra&ram=96)

General · Alibaba · 2025-08-05

Q8\_0Excellent

5.0 GB5% of RAM~160 tok/sEstimated4.02B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Ilama 3.2 1B](/fit/hmellor-ilama-3-2-1b?chip=m5-ultra&ram=96)

General · hmellor · 2025-07-22

Q8\_0Excellent

1.9 GB2% of RAM~519 tok/sEstimated1.24B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[NVIDIA Nemotron Nano 9B v2](/fit/nvidia-nvidia-nemotron-nano-9b-v2?chip=m5-ultra&ram=96)

General · nvidia · 2025-08-12

Q8\_0Excellent

10.4 GB11% of RAM~72 tok/sEstimated8.89B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 h tiny](/fit/ibm-granite-granite-4-0-h-tiny?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

8.2 GB9% of RAMBenchmark needed6.94B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[droplychee 1.0 27b](/fit/droplychee-droplychee-1-0-27b?chip=m5-ultra&ram=96)

Multimodal · droplychee · 2026-07-17

Q8\_0Excellent

31.5 GB33% of RAM~23 tok/sEstimated27.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 micro](/fit/ibm-granite-granite-4-0-micro?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

4.3 GB4% of RAM~189 tok/sEstimated3.4B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 VL 450M](/fit/liquidai-lfm2-vl-450m?chip=m5-ultra&ram=96)

Multimodal · Liquid AI · 2025-08-12

Q8\_0Excellent

1.0 GB1% of RAM~1,429 tok/sEstimated0.45B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Olmo 3 1025 7B](/fit/allenai-olmo-3-1025-7b?chip=m5-ultra&ram=96)

General · allenai · 2025-09-12

Q8\_0Excellent

8.6 GB9% of RAM~88 tok/sEstimated7.3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gpt oss safeguard 20b](/fit/openai-gpt-oss-safeguard-20b?chip=m5-ultra&ram=96)

General · openai · 2025-09-18

Q8\_0Excellent

24.5 GB26% of RAMBenchmark needed21.51B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.8 27B](/fit/qwen-qwen3-8-27b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-08-05

Q8\_0Excellent

31.5 GB33% of RAM~23 tok/sEstimated27.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3 8B DFlash b16](/fit/z-lab-qwen3-8b-dflash-b16?chip=m5-ultra&ram=96)

General · z-lab · 2026-01-04

Q8\_0Excellent

9.4 GB10% of RAM~80 tok/sEstimated8B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3 30B A3B Thinking 2507](/fit/qwen-qwen3-30b-a3b-thinking-2507?chip=m5-ultra&ram=96)

General · Alibaba · 2025-07-29

Q8\_0Excellent

34.6 GB36% of RAMBenchmark needed30.53B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 h small](/fit/ibm-granite-granite-4-0-h-small?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

36.4 GB38% of RAMBenchmark needed32.21B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled](/fit/jackrong-qwen3-5-27b-claude-4-6-opus-reasoning-distilled?chip=m5-ultra&ram=96)

Reasoning · jackrong · 2026-02-27

Q8\_0Excellent

31.5 GB33% of RAM~23 tok/sEstimated27.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[XCurOS0.1 8B Instruct](/fit/xcuros-xcuros0-1-8b-instruct?chip=m5-ultra&ram=96)

Chat · xcuros · 2026-02-28

Q8\_0Excellent

9.0 GB9% of RAM~84 tok/sEstimated7.62B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[OneRec 1.7B](/fit/openonerec-onerec-1-7b?chip=m5-ultra&ram=96)

General · openonerec · 2025-12-30

Q8\_0Excellent

2.9 GB3% of RAM~302 tok/sEstimated2.13B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 h micro](/fit/ibm-granite-granite-4-0-h-micro?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

4.1 GB4% of RAM~202 tok/sEstimated3.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Ouro 1.4B](/fit/bytedance-ouro-1-4b?chip=m5-ultra&ram=96)

General · bytedance · 2025-10-28

Q8\_0Excellent

2.1 GB2% of RAM~450 tok/sEstimated1.43B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3 4B DFlash b16](/fit/z-lab-qwen3-4b-dflash-b16?chip=m5-ultra&ram=96)

General · z-lab · 2026-01-04

Q8\_0Excellent

5.0 GB5% of RAM~161 tok/sEstimated4B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 VL 1.6B](/fit/liquidai-lfm2-vl-1-6b?chip=m5-ultra&ram=96)

Multimodal · Liquid AI · 2025-08-12

Q8\_0Excellent

2.3 GB2% of RAM~407 tok/sEstimated1.58B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 2.6B](/fit/liquidai-lfm2-2-6b?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-22

Q8\_0Excellent

3.4 GB4% of RAM~250 tok/sEstimated2.57B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 350M PII Extract JP](/fit/liquidai-lfm2-350m-pii-extract-jp?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-30

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 1.2B Extract](/fit/liquidai-lfm2-1-2b-extract?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-08-22

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 350M ENJP MT](/fit/liquidai-lfm2-350m-enjp-mt?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 1.2B RAG](/fit/liquidai-lfm2-1-2b-rag?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 350M Math](/fit/liquidai-lfm2-350m-math?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-08-25

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 350M Extract](/fit/liquidai-lfm2-350m-extract?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 1.2B Tool](/fit/liquidai-lfm2-1-2b-tool?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[VAETKI 20B A2B](/fit/nc-ai-consortium-vaetki-20b-a2b?chip=m5-ultra&ram=96)

General · NCAI · 2025-12-29

Q8\_0Excellent

22.4 GB23% of RAMBenchmark needed19.6B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[VAETKI 7B A1B](/fit/nc-ai-consortium-vaetki-7b-a1b?chip=m5-ultra&ram=96)

General · NCAI · 2025-12-29

Q8\_0Excellent

8.6 GB9% of RAMBenchmark needed7.25B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.6 27B](/fit/qwen-qwen3-6-27b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-04-21

Q8\_0Excellent

31.5 GB33% of RAM~23 tok/sEstimated27.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[DeepSeek R1 0528 Qwen3 8B](/fit/deepseek-ai-deepseek-r1-0528-qwen3-8b?chip=m5-ultra&ram=96)

Reasoning · DeepSeek · 2025-05-29

Q8\_0Excellent

9.6 GB10% of RAM~79 tok/sEstimated8.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Olmo 3 7B Instruct](/fit/allenai-olmo-3-7b-instruct?chip=m5-ultra&ram=96)

Chat · allenai · 2025-11-19

Q8\_0Excellent

8.6 GB9% of RAM~88 tok/sEstimated7.3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Olmo 3 7B Instruct SFT](/fit/allenai-olmo-3-7b-instruct-sft?chip=m5-ultra&ram=96)

Chat · allenai · 2025-11-17

Q8\_0Excellent

8.6 GB9% of RAM~88 tok/sEstimated7.3B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[NVIDIA Nemotron Nano 12B v2](/fit/nvidia-nvidia-nemotron-nano-12b-v2?chip=m5-ultra&ram=96)

General · nvidia · 2025-08-21

Q8\_0Excellent

13.9 GB14% of RAM~54 tok/sEstimated12B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[avibe](/fit/avitotech-avibe?chip=m5-ultra&ram=96)

General · avitotech · 2025-10-20

Q8\_0Excellent

9.3 GB10% of RAM~81 tok/sEstimated7.9B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LLaDA2.0 mini](/fit/inclusionai-llada2-0-mini?chip=m5-ultra&ram=96)

General · inclusionai · 2025-11-25

Q8\_0Excellent

18.6 GB19% of RAMBenchmark needed16.26B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 tiny preview](/fit/ibm-granite-granite-4-0-tiny-preview?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-04-30

Q8\_0Excellent

7.9 GB8% of RAMBenchmark needed6.67B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 1.2B](/fit/liquidai-lfm2-1-2b?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

1.8 GB2% of RAM~550 tok/sEstimated1.17B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Phi 4 mini reasoning](/fit/microsoft-phi-4-mini-reasoning?chip=m5-ultra&ram=96)

Reasoning · Microsoft · 2025-04-29

Q8\_0Excellent

4.8 GB5% of RAM~168 tok/sEstimated3.84B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[MiniCPM4.1 8B](/fit/openbmb-minicpm4-1-8b?chip=m5-ultra&ram=96)

General · openbmb · 2025-09-02

Q8\_0Excellent

9.6 GB10% of RAM~79 tok/sEstimated8.19B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[PARD Llama 3.2 1B](/fit/amd-pard-llama-3-2-1b?chip=m5-ultra&ram=96)

General · amd · 2025-05-17

Q8\_0Excellent

2.2 GB2% of RAM~429 tok/sEstimated1.5B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[newsvibe categories multilingual llama 1b](/fit/stefanruseti-newsvibe-categories-multilingual-llama-1b?chip=m5-ultra&ram=96)

General · stefanruseti · 2025-06-04

Q8\_0Excellent

1.9 GB2% of RAM~519 tok/sEstimated1.24B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[granite 4.0 350m base](/fit/ibm-granite-granite-4-0-350m-base?chip=m5-ultra&ram=96)

General · ibm-granite · 2025-10-07

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[EuroLLM 9B Instruct 2512](/fit/utter-project-eurollm-9b-instruct-2512?chip=m5-ultra&ram=96)

Chat · utter-project · 2026-01-26

Q8\_0Excellent

10.7 GB11% of RAM~70 tok/sEstimated9.15B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[EXAONE 4.0 1.2B](/fit/lgai-exaone-exaone-4-0-1-2b?chip=m5-ultra&ram=96)

General · lgai-exaone · 2025-07-11

Q8\_0Excellent

1.9 GB2% of RAM~503 tok/sEstimated1.28B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 350M](/fit/liquidai-lfm2-350m?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

0.9 GB1% of RAM~1,838 tok/sEstimated0.35B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Jan nano 128k](/fit/menlo-jan-nano-128k?chip=m5-ultra&ram=96)

General · menlo · 2025-06-25

Q8\_0Excellent

5.0 GB5% of RAM~160 tok/sEstimated4.02B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[LFM2 700M](/fit/liquidai-lfm2-700m?chip=m5-ultra&ram=96)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

1.3 GB1% of RAM~869 tok/sEstimated0.74B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma 3 12b it abliterated v2](/fit/mlabonne-gemma-3-12b-it-abliterated-v2?chip=m5-ultra&ram=96)

Multimodal · mlabonne · 2025-05-28

Q8\_0Excellent

13.6 GB14% of RAM~55 tok/sEstimated11.77B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[VAETKI VL 7B A1B](/fit/nc-ai-consortium-vaetki-vl-7b-a1b?chip=m5-ultra&ram=96)

Multimodal · NCAI · 2025-12-29

Q8\_0Excellent

9.0 GB9% of RAMBenchmark needed7.58B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen2.5 VL 7B Instruct](/fit/qwen-qwen2-5-vl-7b-instruct?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2025-01-26

Q8\_0Excellent

9.7 GB10% of RAM~78 tok/sEstimated8.29B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen2.5 VL 3B Instruct](/fit/qwen-qwen2-5-vl-3b-instruct?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2025-01-26

Q8\_0Excellent

4.7 GB5% of RAM~172 tok/sEstimated3.75B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3.5 27B](/fit/qwen-qwen3-5-27b?chip=m5-ultra&ram=96)

Multimodal · Alibaba · 2026-02-24

Q8\_0Excellent

31.5 GB33% of RAM~23 tok/sEstimated27.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[SmolLM3 3B](/fit/huggingfacetb-smollm3-3b?chip=m5-ultra&ram=96)

General · huggingfacetb · 2025-07-08

Q8\_0Excellent

3.9 GB4% of RAM~209 tok/sEstimated3.08B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[DeepSeek R1 Distill Qwen 1.5B](/fit/deepseek-ai-deepseek-r1-distill-qwen-1-5b?chip=m5-ultra&ram=96)

Reasoning · DeepSeek · 2025-01-20

Q8\_0Excellent

2.5 GB3% of RAM~361 tok/sEstimated1.78B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3Guard Gen 4B](/fit/qwen-qwen3guard-gen-4b?chip=m5-ultra&ram=96)

General · Alibaba · 2025-09-23

Q8\_0Excellent

5.4 GB6% of RAM~146 tok/sEstimated4.41B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[DeepSeek R1 Distill Llama 8B](/fit/deepseek-ai-deepseek-r1-distill-llama-8b?chip=m5-ultra&ram=96)

Reasoning · DeepSeek · 2025-01-20

Q8\_0Excellent

9.5 GB10% of RAM~80 tok/sEstimated8.03B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[DeepSeek R1 Distill Qwen 7B](/fit/deepseek-ai-deepseek-r1-distill-qwen-7b?chip=m5-ultra&ram=96)

Reasoning · DeepSeek · 2025-01-20

Q8\_0Excellent

9.0 GB9% of RAM~84 tok/sEstimated7.62B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[gemma4 e4b claims comparison](/fit/k-chirkunov-gemma4-e4b-claims-comparison?chip=m5-ultra&ram=96)

General · k-chirkunov · 2026-07-14

Q8\_0Excellent

9.4 GB10% of RAM~81 tok/sEstimated7.94B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[SmolLM3 3B Base](/fit/huggingfacetb-smollm3-3b-base?chip=m5-ultra&ram=96)

General · huggingfacetb · 2025-06-19

Q8\_0Excellent

3.9 GB4% of RAM~209 tok/sEstimated3.08B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

[Qwen3Guard Gen 0.6B](/fit/qwen-qwen3guard-gen-0-6b?chip=m5-ultra&ram=96)

General · Alibaba · 2025-09-23

Q8\_0Excellent

1.3 GB1% of RAM~858 tok/sEstimated0.75B params

What Mac for this model? [Run with ToolPiper](/toolpiper)

Show more (6413 remaining)

## 64-core vs 80-core GPU

Both bins run the same 1228 GB/s memory bus, so token generation is the same on either one. The extra cores show up in image and video work, not in tokens per second.

| Configuration | Memory bandwidth | Memory options | Models that fit |
| --- | --- | --- | --- |
| 30-core CPU, 64-core GPU | 1228 GB/s | 96 GB | Identical |
| 36-core CPU, 80-core GPU | 1228 GB/s | 256, 512 GB | Identical |

## Measured on the M5 Ultra

Nobody has submitted a benchmark on the M5 Ultra yet, so every speed on this page is the formula estimate rather than a measured run. The estimate is bandwidth-driven and calibrated against chips that do have data, which makes it a good guide and not a promise.

ToolPiper contributes a result anonymously when you run the benchmark, and the [leaderboard](/fit/benchmarks) shows every chip that already has one.

## Where to go from here

What each step actually changes for local models, rather than which one is newer.

[Used market alternative

Mac Studio M3 Ultra

33% less memory bandwidth

](/mac-studio/m3-ultra)

## Why unified memory is the number that matters

On a PC the model has to fit in GPU VRAM, which is a separate pool from system RAM and usually the smaller of the two. Apple Silicon has one pool. The M5 Ultra's 1228 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 512 GB machine can hand almost all of that to a model with no copy across a bus.

The Studio exists for this workload. It carries the widest memory buses and the highest capacities Apple sells, and it runs at full clocks indefinitely. Buy the memory, not the cores: every extra GB raises what you can load, while the core count only moves throughput on models that already fit.

## Common questions

### Can the M5 Ultra Mac Studio run a 70B model?

Yes, at 512 GB. A 70B model at Q4\_K\_M needs about 46 GB including an 8K context, and 512 GB of unified memory leaves about 450 GB for weights once macOS takes its share. At 96 GB it does not fit at any quantization worth running.

### How much unified memory should I get with the M5 Ultra Mac Studio?

Memory is the only spec that changes what you can run at all. 96 GB holds about a 129B model at Q4; 512 GB holds about 696B. It is soldered, so this is a one-time decision, and it is the upgrade worth paying for before core count.

### How fast are local LLMs on the M5 Ultra?

Token generation is bandwidth-bound, so M5 Ultra throughput scales with its 1228 GB/s memory bus. Divide bandwidth by the size of the weights actually read per token to get the ceiling, then expect roughly half of that in practice. A 7B model at Q4 reads about 4 GB per token pass, so the M5 Ultra lands in the tens of tokens per second and a 70B model lands in the single digits.

### Is the 80-core GPU worth it over the 64-core on the M5 Ultra?

Not for LLMs. Both bins run the same 1228 GB/s memory bus and take the same memory options, and token generation is bound by bandwidth rather than GPU cores. The extra cores show up in image generation and video work, not in tokens per second.

### Should I buy the M5 Ultra Mac Studio now or wait for the next one?

Buy on the memory you need today. Apple raises memory ceilings slowly and bandwidth in steps, and the M5 Ultra already holds about a 696B model at Q4. If your target model fits in 512 GB, waiting buys throughput rather than capability.

## Run these models on your Mac Studio

ToolPiper downloads, manages, and runs local models on Apple Silicon. Free, and nothing leaves the machine.

[Get ToolPiper](/toolpiper)[Compare against another Mac](/fit?chip=m5-ultra&ram=96)

[![ModelPiper](modelpiper-logo-sm.png)ModelPiper](/)

Runs on ToolPiper  
Local AI  
Private by default  
Talk to your Mac

#### Products

-   [ToolPiper](/toolpiper)
-   [VisionPiper](/visionpiper)
-   [AudioPiper](/audiopiper)
-   [MediaPiper](/docs/mediapiper)
-   [PiperTest](/pipertest)

#### Mac Hardware

-   [MacBook Air](/macbook-air)
-   [MacBook Pro 14"](/macbook-pro-14)
-   [MacBook Pro 16"](/macbook-pro-16)
-   [Mac mini](/mac-mini)
-   [Mac Studio](/mac-studio)
-   [iMac](/imac)

#### Resources

-   [Model Fit](/fit)
-   [Benchmarks](/fit/benchmarks)
-   [Blog](/blog)
-   [Workflows](/workflow)
-   [Docs](/docs)
-   [MCP Tools](/mcp-tools)

#### Company

-   [About](/about)
-   [Press](/press)
-   [Changelog](/changelog)
-   [Pricing](/pricing)
-   [Download](/download)
-   [Privacy](/privacy)
-   [Terms](/terms)

© 2026 ModelPiper. All rights reserved.