---
title: "Mac mini M6: What AI Models Can It Run? | ModelPiper"
description: "Local AI on the M6 Mac mini: 153 to 170 GB/s memory bandwidth and 16 to 32 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run."
canonical: "https://modelpiper.com/mac-mini/m6"
---

# Mac mini M6: What AI Models Can It Run? | ModelPiper

> Local AI on the M6 Mac mini: 153 to 170 GB/s memory bandwidth and 16 to 32 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run.

[← All Mac mini models](/mac-mini)

# Mac mini M6

The M6 Mac mini runs local models at 153 to 170 GB/s of memory bandwidth with 16 to 32 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 32 GB you can hold roughly a 42B dense model at Q4. A base M chip is the narrow end of the memory bus. It runs small models pleasantly and stops hard at the memory ceiling, which is the constraint you will hit first.

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

## Specifications

ChipApple M6

CPU cores12

GPU cores12

Unified memory16, 24, or 32 GB

Memory bandwidth153 to 170 GB/s

Neural Engine76 TOPS

Released2026

AvailabilitySold new by Apple

Memory bandwidth is faster than 30% of the Apple Silicon chips shipped in a Mac, against a 1228 GB/s peak.

Its memory ceiling is above 15% 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.

Unified memory

16 GB24 GB32 GB

## What each memory option runs

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

[16 GB](#ram-16gb)[24 GB](#ram-24gb)[32 GB](#ram-32gb)

### 16 GB unified memory

14 GB usable for weights · 153 GB/s

5,572 of 6,563 models fit, and 5,054 of them run with headroom rather than as a squeeze.

Largest model at Q4

[maple preview](/fit/deepgrove-maple-preview) · 20.21B

Best all-round pick

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b) · Q8\_0 · ~74 tok/s

### 24 GB unified memory

21 GB usable for weights · 170 GB/s

6,032 of 6,563 models fit, and 5,271 of them run with headroom rather than as a squeeze.

Largest model at Q4

[W2 31B A3B dLLM Base preview](/fit/whaletechai-w2-31b-a3b-dllm-base-preview) · 31.12B

Best all-round pick

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b) · Q8\_0 · ~82 tok/s

### 32 GB unified memory

28 GB usable for weights · 170 GB/s

6,082 of 6,563 models fit, and 5,571 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Phi 3.5 MoE instruct](/fit/microsoft-phi-3-5-moe-instruct) · 41.87B

Best all-round pick

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b) · Q8\_0 · ~82 tok/s

## What a 16 GB M6 Mac mini can run

Every model in the database against this exact configuration, at 153 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

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b?chip=m6&ram=16)

General · openbmb · 2026-05-21

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[LFM2.5 230M](/fit/liquidai-lfm2-5-230m?chip=m6&ram=16)

General · Liquid AI · 2026-06-24

Q8\_0Excellent

0.8 GB5% of RAM~348 tok/sEstimated0.23B params

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

[minicpm5 1b hermes toolhv1](/fit/ktruestory-minicpm5-1b-hermes-toolhv1?chip=m6&ram=16)

General · ktruestory · 2026-05-28

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[FrankenCPM 4x1B A2B](/fit/petrouil-frankencpm-4x1b-a2b?chip=m6&ram=16)

General · petrouil · 2026-07-23

Q8\_0Excellent

3.4 GB21% of RAMBenchmark needed2.61B params

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

[LFM2.5 350M](/fit/liquidai-lfm2-5-350m?chip=m6&ram=16)

General · Liquid AI · 2026-03-31

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b?chip=m6&ram=16)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB9% of RAM~92 tok/sEstimated0.87B params

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

[Kimi K3 DSpark](/fit/radixark-kimi-k3-dspark?chip=m6&ram=16)

General · radixark · 2026-07-27

Q8\_0Excellent

3.0 GB19% of RAM~36 tok/sEstimated2.25B params

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

[Qwen3.5 0.8B Base](/fit/qwen-qwen3-5-0-8b-base?chip=m6&ram=16)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB9% of RAM~92 tok/sEstimated0.87B params

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

[JOSIE 2 2B OSS](/fit/goekdeniz-guelmez-josie-2-2b-oss?chip=m6&ram=16)

General · goekdeniz-guelmez · 2026-07-31

Q8\_0Excellent

3.0 GB19% of RAM~35 tok/sEstimated2.27B params

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

[pii guard turkish 270m](/fit/cagrigungor-pii-guard-turkish-270m?chip=m6&ram=16)

General · cagrigungor · 2026-08-06

Q8\_0Excellent

0.8 GB5% of RAM~297 tok/sEstimated0.27B params

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

[Qwen3.5 2B](/fit/qwen-qwen3-5-2b?chip=m6&ram=16)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB19% of RAM~35 tok/sEstimated2.27B params

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

[Qwen3.5 2B Base](/fit/qwen-qwen3-5-2b-base?chip=m6&ram=16)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB19% of RAM~35 tok/sEstimated2.27B params

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

[LFM2.5 8B A1B](/fit/liquidai-lfm2-5-8b-a1b?chip=m6&ram=16)

General · Liquid AI · 2026-05-28

Q8\_0Excellent

9.9 GB62% of RAMBenchmark needed8.47B params

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

[LFM2.5 2.6B](/fit/liquidai-lfm2-5-2-6b?chip=m6&ram=16)

General · Liquid AI · 2026-07-28

Q8\_0Excellent

3.5 GB22% of RAM~30 tok/sEstimated2.7B params

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

[LFM2.5 VL 1.6B](/fit/liquidai-lfm2-5-vl-1-6b?chip=m6&ram=16)

Multimodal · Liquid AI · 2026-01-05

Q8\_0Excellent

2.3 GB14% of RAM~50 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=m6&ram=16)

General · Liquid AI · 2026-01-20

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[OneReason 0.8B pretrain competition](/fit/openonerec-onereason-0-8b-pretrain-competition?chip=m6&ram=16)

Reasoning · openonerec · 2026-06-09

Q8\_0Excellent

1.4 GB9% of RAM~100 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=m6&ram=16)

General · Liquid AI · 2026-01-05

Q8\_0Excellent

1.8 GB11% of RAM~68 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=m6&ram=16)

General · Liquid AI · 2026-01-04

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[LFM2.5 1.2B Instruct](/fit/liquidai-lfm2-5-1-2b-instruct?chip=m6&ram=16)

Chat · Liquid AI · 2026-01-06

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[LFM2 ColBERT 350M](/fit/liquidai-lfm2-colbert-350m?chip=m6&ram=16)

General · Liquid AI · 2025-10-28

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[Lumma 0.6B Extract](/fit/frontiersmind-lumma-0-6b-extract?chip=m6&ram=16)

General · frontiersmind · 2026-08-03

Q8\_0Excellent

1.2 GB8% of RAM~123 tok/sEstimated0.65B params

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

[OTel LLM 8B A1B IT](/fit/farbodtavakkoli-otel-llm-8b-a1b-it?chip=m6&ram=16)

General · farbodtavakkoli · 2026-06-17

Q8\_0Excellent

10.8 GB67% of RAMBenchmark needed9.23B params

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

[Ilama 3.2 1B](/fit/hmellor-ilama-3-2-1b?chip=m6&ram=16)

General · hmellor · 2025-07-22

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[granite 4.0 h tiny](/fit/ibm-granite-granite-4-0-h-tiny?chip=m6&ram=16)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

8.2 GB52% of RAMBenchmark needed6.94B params

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

[LFM2 VL 450M](/fit/liquidai-lfm2-vl-450m?chip=m6&ram=16)

Multimodal · Liquid AI · 2025-08-12

Q8\_0Excellent

1.0 GB6% of RAM~178 tok/sEstimated0.45B params

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

[LFM2 350M PII Extract JP](/fit/liquidai-lfm2-350m-pii-extract-jp?chip=m6&ram=16)

General · Liquid AI · 2025-09-30

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 1.2B Extract](/fit/liquidai-lfm2-1-2b-extract?chip=m6&ram=16)

General · Liquid AI · 2025-08-22

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[LFM2 350M ENJP MT](/fit/liquidai-lfm2-350m-enjp-mt?chip=m6&ram=16)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 1.2B RAG](/fit/liquidai-lfm2-1-2b-rag?chip=m6&ram=16)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[LFM2 350M Math](/fit/liquidai-lfm2-350m-math?chip=m6&ram=16)

General · Liquid AI · 2025-08-25

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 350M Extract](/fit/liquidai-lfm2-350m-extract?chip=m6&ram=16)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 1.2B Tool](/fit/liquidai-lfm2-1-2b-tool?chip=m6&ram=16)

General · Liquid AI · 2025-09-03

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[LFM2 2.6B Transcript](/fit/liquidai-lfm2-2-6b-transcript?chip=m6&ram=16)

General · Liquid AI · 2026-01-05

Q8\_0Excellent

3.4 GB21% of RAM~31 tok/sEstimated2.57B params

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

[VibeThinker 3B](/fit/weiboai-vibethinker-3b?chip=m6&ram=16)

General · weiboai · 2026-06-12

Q8\_0Excellent

3.9 GB25% of RAM~26 tok/sEstimated3.09B params

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

[granite 4.0 tiny preview](/fit/ibm-granite-granite-4-0-tiny-preview?chip=m6&ram=16)

General · ibm-granite · 2025-04-30

Q8\_0Excellent

7.9 GB50% of RAMBenchmark needed6.67B params

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

[LFM2 1.2B](/fit/liquidai-lfm2-1-2b?chip=m6&ram=16)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[newsvibe categories multilingual llama 1b](/fit/stefanruseti-newsvibe-categories-multilingual-llama-1b?chip=m6&ram=16)

General · stefanruseti · 2025-06-04

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[Qwen3.8\_4B\_Distilled\_GGUF](/fit/ma7ee7-qwen3-8_4b_distilled_gguf?chip=m6&ram=16)

General · ma7ee7 · 2026-07-30

Q8\_0Excellent

4.0 GB25% of RAM~26 tok/sEstimated3.13B params

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

[Ouro 1.4B](/fit/bytedance-ouro-1-4b?chip=m6&ram=16)

General · bytedance · 2025-10-28

Q8\_0Excellent

2.1 GB13% of RAM~56 tok/sEstimated1.43B params

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

[granite 4.0 350m base](/fit/ibm-granite-granite-4-0-350m-base?chip=m6&ram=16)

General · ibm-granite · 2025-10-07

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 VL 1.6B](/fit/liquidai-lfm2-vl-1-6b?chip=m6&ram=16)

Multimodal · Liquid AI · 2025-08-12

Q8\_0Excellent

2.3 GB14% of RAM~51 tok/sEstimated1.58B params

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

[EXAONE 4.0 1.2B](/fit/lgai-exaone-exaone-4-0-1-2b?chip=m6&ram=16)

General · lgai-exaone · 2025-07-11

Q8\_0Excellent

1.9 GB12% of RAM~63 tok/sEstimated1.28B params

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

[LFM2 350M](/fit/liquidai-lfm2-350m?chip=m6&ram=16)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2 700M](/fit/liquidai-lfm2-700m?chip=m6&ram=16)

General · Liquid AI · 2025-07-10

Q8\_0Excellent

1.3 GB8% of RAM~108 tok/sEstimated0.74B params

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

[LFM2 2.6B Exp](/fit/liquidai-lfm2-2-6b-exp?chip=m6&ram=16)

General · Liquid AI · 2025-12-25

Q8\_0Excellent

3.4 GB21% of RAM~31 tok/sEstimated2.57B params

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

[VAETKI 7B A1B](/fit/nc-ai-consortium-vaetki-7b-a1b?chip=m6&ram=16)

General · NCAI · 2025-12-29

Q8\_0Excellent

8.6 GB54% of RAMBenchmark needed7.25B params

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

[granite vision 4.1 4b](/fit/ibm-granite-granite-vision-4-1-4b?chip=m6&ram=16)

Multimodal · ibm-granite · 2026-04-16

Q8\_0Excellent

5.0 GB31% of RAM~20 tok/sEstimated4B params

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

[Qwen3Guard Gen 0.6B](/fit/qwen-qwen3guard-gen-0-6b?chip=m6&ram=16)

General · Alibaba · 2025-09-23

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[OneRec 1.7B](/fit/openonerec-onerec-1-7b?chip=m6&ram=16)

General · openonerec · 2025-12-30

Q8\_0Excellent

2.9 GB18% of RAM~38 tok/sEstimated2.13B params

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

[PARD Llama 3.2 1B](/fit/amd-pard-llama-3-2-1b?chip=m6&ram=16)

General · amd · 2025-05-17

Q8\_0Excellent

2.2 GB14% of RAM~53 tok/sEstimated1.5B params

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

[plamo 2 1b](/fit/pfnet-plamo-2-1b?chip=m6&ram=16)

General · pfnet · 2025-02-05

Q8\_0Excellent

1.9 GB12% of RAM~62 tok/sEstimated1.29B params

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

[HRM Text 1B](/fit/sapientinc-hrm-text-1b?chip=m6&ram=16)

General · sapientinc · 2026-05-17

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.18B params

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

[LFM2 VL 3B](/fit/liquidai-lfm2-vl-3b?chip=m6&ram=16)

Multimodal · Liquid AI · 2025-10-22

Q8\_0Excellent

3.8 GB24% of RAM~27 tok/sEstimated3B params

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

[LFM2 2.6B](/fit/liquidai-lfm2-2-6b?chip=m6&ram=16)

General · Liquid AI · 2025-09-22

Q8\_0Excellent

3.4 GB21% of RAM~31 tok/sEstimated2.57B params

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

[MicroLlama v2](/fit/viorikaai-org-microllama-v2?chip=m6&ram=16)

General · viorikaai-org · 2026-07-05

Q8\_0Excellent

0.6 GB3% of RAM~1,603 tok/sEstimated0.05B params

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

[BananaMind 2 Nano](/fit/bananamind-bananamind-2-nano?chip=m6&ram=16)

General · bananamind · 2026-07-17

Q8\_0Excellent

0.5 GB3% of RAM~8,014 tok/sEstimated0.01B params

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

[Nexus Erebus 50M](/fit/maliosdark-nexus-erebus-50m?chip=m6&ram=16)

General · maliosdark · 2026-07-09

Q8\_0Excellent

0.6 GB3% of RAM~1,603 tok/sEstimated0.05B params

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

[Jolia](/fit/raidium-jolia?chip=m6&ram=16)

General · raidium · 2026-06-15

Q8\_0Excellent

0.5 GB3% of RAM~4,007 tok/sEstimated0.02B params

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

[VAETKI VL 7B A1B](/fit/nc-ai-consortium-vaetki-vl-7b-a1b?chip=m6&ram=16)

Multimodal · NCAI · 2025-12-29

Q8\_0Excellent

9.0 GB56% of RAMBenchmark needed7.58B params

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

[embeddinggemma GTAIDE 300m 2605](/fit/taide-embeddinggemma-gtaide-300m-2605?chip=m6&ram=16)

Embedding · taide · 2026-06-12

Q8\_0Excellent

0.8 GB5% of RAM~267 tok/sEstimated0.3B params

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

[Qwen3 0.6B](/fit/qwen-qwen3-0-6b?chip=m6&ram=16)

General · Alibaba · 2025-04-27

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[GLM OCR](/fit/zai-org-glm-ocr?chip=m6&ram=16)

Multimodal · zai-org

Q8\_0Excellent

2.0 GB12% of RAM~60 tok/sEstimated1.33B params

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

[surya ocr 2](/fit/datalab-to-surya-ocr-2?chip=m6&ram=16)

Multimodal · datalab-to

Q8\_0Excellent

1.3 GB8% of RAM~116 tok/sEstimated0.69B params

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

[MiniCPM V 4.6](/fit/openbmb-minicpm-v-4-6?chip=m6&ram=16)

Multimodal · openbmb

Q8\_0Excellent

2.0 GB12% of RAM~62 tok/sEstimated1.3B params

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

[Qwen3 0.6B Base](/fit/qwen-qwen3-0-6b-base?chip=m6&ram=16)

General · Alibaba · 2025-04-28

Q8\_0Excellent

1.2 GB7% of RAM~134 tok/sEstimated0.6B 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=m6&ram=16)

Reasoning · DeepSeek · 2025-01-20

Q8\_0Excellent

2.5 GB16% of RAM~45 tok/sEstimated1.78B params

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

[HunyuanOCR](/fit/tencent-hunyuanocr?chip=m6&ram=16)

Multimodal · tencent

Q8\_0Excellent

1.7 GB11% of RAMBenchmark needed1.12B params

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

[distil lfm25 shellper](/fit/distil-labs-distil-lfm25-shellper?chip=m6&ram=16)

General · distil-labs

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[OTel LLM 1.2B IT](/fit/farbodtavakkoli-otel-llm-1-2b-it?chip=m6&ram=16)

General · farbodtavakkoli

Q8\_0Excellent

1.8 GB12% of RAM~66 tok/sEstimated1.21B params

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

[OvisOCR2](/fit/ath-maas-ovisocr2?chip=m6&ram=16)

Multimodal · ath-maas

Q8\_0Excellent

1.4 GB9% of RAM~94 tok/sEstimated0.85B params

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

[LFM2.5 VL 450M](/fit/liquidai-lfm2-5-vl-450m?chip=m6&ram=16)

Multimodal · Liquid AI

Q8\_0Excellent

1.0 GB6% of RAM~178 tok/sEstimated0.45B params

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

[PaddleOCR VL 1.6](/fit/paddlepaddle-paddleocr-vl-1-6?chip=m6&ram=16)

Multimodal · paddlepaddle

Q8\_0Excellent

1.6 GB10% of RAM~83 tok/sEstimated0.96B params

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

[LFM2.5 350M Base](/fit/liquidai-lfm2-5-350m-base?chip=m6&ram=16)

General · Liquid AI

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[alloma 1B Instruct](/fit/uzlm-alloma-1b-instruct?chip=m6&ram=16)

Chat · uzlm · 2025-09-03

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[LFM2 8B A1B](/fit/liquidai-lfm2-8b-a1b?chip=m6&ram=16)

General · Liquid AI · 2025-10-07

Q8\_0Excellent

9.8 GB61% of RAMBenchmark needed8.34B params

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

[PaddleOCR VL](/fit/paddlepaddle-paddleocr-vl?chip=m6&ram=16)

Multimodal · paddlepaddle

Q8\_0Excellent

1.6 GB10% of RAM~83 tok/sEstimated0.96B params

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

[AI21 Jamba2 3B](/fit/ai21labs-ai21-jamba2-3b?chip=m6&ram=16)

General · ai21labs · 2026-01-06

Q8\_0Excellent

3.9 GB24% of RAMBenchmark needed3.03B params

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

[Orpo Llama 3.2 1B 15k](/fit/adamlucek-orpo-llama-3-2-1b-15k?chip=m6&ram=16)

General · adamlucek

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[llama 3.2 1b code instruct](/fit/shahriarferdoush-llama-3-2-1b-code-instruct?chip=m6&ram=16)

Coding · shahriarferdoush

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[Llama 3.2 1B Aegis SFT DPO](/fit/ahczhg-llama-3-2-1b-aegis-sft-dpo?chip=m6&ram=16)

General · ahczhg

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[Qwen3 0.6B ONNX](/fit/onnx-community-qwen3-0-6b-onnx?chip=m6&ram=16)

General · onnx-community · 2025-04-28

Q8\_0Excellent

1.0 GB6% of RAM~178 tok/sEstimated0.45B params

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

[Tashkeel 700M](/fit/etherll-tashkeel-700m?chip=m6&ram=16)

General · etherll

Q8\_0Excellent

1.3 GB8% of RAM~108 tok/sEstimated0.74B params

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

[ERNIE 4.5 0.3B PT](/fit/baidu-ernie-4-5-0-3b-pt?chip=m6&ram=16)

General · baidu

Q8\_0Excellent

0.9 GB6% of RAM~223 tok/sEstimated0.36B params

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

[LFM2.5 1.2B JP 202606](/fit/liquidai-lfm2-5-1-2b-jp-202606?chip=m6&ram=16)

General · Liquid AI

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[MiniCPM5 1B Base](/fit/openbmb-minicpm5-1b-base?chip=m6&ram=16)

General · openbmb

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[Llama 3.2 1B flax](/fit/benjamin-llama-3-2-1b-flax?chip=m6&ram=16)

General · benjamin

Q8\_0Excellent

1.7 GB11% of RAM~75 tok/sEstimated1.07B params

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

[LFM2 1.2B ONNX](/fit/lemonelabs-lfm2-1-2b-onnx?chip=m6&ram=16)

General · lemonelabs

Q8\_0Excellent

1.8 GB12% of RAM~66 tok/sEstimated1.21B params

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

[MiniCPM4 0.5B](/fit/openbmb-minicpm4-0-5b?chip=m6&ram=16)

General · openbmb · 2025-06-05

Q8\_0Excellent

1.0 GB6% of RAM~186 tok/sEstimated0.43B params

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

[OTel LLM 20B IT](/fit/farbodtavakkoli-otel-llm-20b-it?chip=m6&ram=16)

General · farbodtavakkoli

Q8\_0Excellent

2.5 GB15% of RAMBenchmark needed1.77B params

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

[LFM2.5 1.2B Nova Function Calling](/fit/novachronoai-lfm2-5-1-2b-nova-function-calling-gguf?chip=m6&ram=16)

General · novachronoai

Q8\_0Excellent

1.8 GB12% of RAM~66 tok/sEstimated1.21B params

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

[PaddleOCR VL 1.5](/fit/paddlepaddle-paddleocr-vl-1-5?chip=m6&ram=16)

Multimodal · paddlepaddle

Q8\_0Excellent

1.6 GB10% of RAM~83 tok/sEstimated0.96B params

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

[FastVLM 0.5B](/fit/kamilamila-fastvlm-0-5b?chip=m6&ram=16)

General · kamilamila

Q8\_0Excellent

1.2 GB7% of RAM~129 tok/sEstimated0.62B params

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

[Trinity Nano Preview](/fit/arcee-ai-trinity-nano-preview?chip=m6&ram=16)

General · arcee-ai

Q8\_0Excellent

7.3 GB46% of RAMBenchmark needed6.12B params

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

[LFM2.5 1.2B JP 202606 ONNX](/fit/liquidai-lfm2-5-1-2b-jp-202606-onnx?chip=m6&ram=16)

General · Liquid AI

Q8\_0Excellent

1.8 GB12% of RAM~66 tok/sEstimated1.21B params

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

[MiniCPM5 1B Claude Opus Fable5 V2 Thinking heretic](/fit/saidutta69-minicpm5-1b-claude-opus-fable5-v2-thinking-heretic?chip=m6&ram=16)

General · saidutta69

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[LFM2.5 350M home assistant sft](/fit/ordenwills-lfm2-5-350m-home-assistant-sft?chip=m6&ram=16)

General · ordenwills

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[Recurrent Llama 3.2 train recurrence 32](/fit/smcleish-recurrent-llama-3-2-train-recurrence-32?chip=m6&ram=16)

General · smcleish

Q8\_0Excellent

2.1 GB13% of RAM~58 tok/sEstimated1.39B params

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

[llama3.2\_1b\_2025\_uncensored\_v2](/fit/carsenk-llama3-2_1b_2025_uncensored_v2?chip=m6&ram=16)

General · carsenk

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[OpenReasoning Nemotron 1.5B](/fit/nvidia-openreasoning-nemotron-1-5b?chip=m6&ram=16)

Reasoning · nvidia

Q8\_0Excellent

2.2 GB14% of RAM~52 tok/sEstimated1.54B params

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

[MiniCPM V 4.6 Thinking](/fit/openbmb-minicpm-v-4-6-thinking?chip=m6&ram=16)

General · openbmb

Q8\_0Excellent

2.0 GB12% of RAM~62 tok/sEstimated1.3B params

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

[granite 4.0 h 1b](/fit/ibm-granite-granite-4-0-h-1b?chip=m6&ram=16)

General · ibm-granite

Q8\_0Excellent

2.1 GB13% of RAM~55 tok/sEstimated1.46B params

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

[gpt oss 120b lora merged redux](/fit/pyoakum-gpt-oss-120b-lora-merged-redux?chip=m6&ram=16)

General · pyoakum

Q8\_0Excellent

6.5 GB40% of RAMBenchmark needed5.35B params

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

[granite 3.1 3b a800m base](/fit/ibm-granite-granite-3-1-3b-a800m-base?chip=m6&ram=16)

General · ibm-granite

Q8\_0Excellent

4.2 GB26% of RAMBenchmark needed3.3B params

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

[MiniCPM V 4.6 Abliterated AND Disinhibited](/fit/treadon-minicpm-v-4-6-abliterated-and-disinhibited?chip=m6&ram=16)

General · treadon

Q8\_0Excellent

2.0 GB12% of RAM~62 tok/sEstimated1.3B params

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

[ODIN C1](/fit/skis-ai-research-odin-c1?chip=m6&ram=16)

General · skis-ai-research

Q8\_0Excellent

1.8 GB11% of RAM~68 tok/sEstimated1.17B params

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

[llama3.2\_1B\_vl](/fit/thkim0305-llama3-2_1b_vl?chip=m6&ram=16)

General · thkim0305

Q8\_0Excellent

1.6 GB10% of RAM~80 tok/sEstimated1B params

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

[Qwen3.5 0.8B Claude 4.6 Opus Reasoning Distilled](/fit/jackrong-qwen3-5-0-8b-claude-4-6-opus-reasoning-distilled?chip=m6&ram=16)

Reasoning · jackrong

Q8\_0Excellent

1.5 GB9% of RAM~92 tok/sEstimated0.87B params

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

[Qwen3.5 0.8B Coder Calude Full](/fit/rahul7star-qwen3-5-0-8b-coder-calude-full?chip=m6&ram=16)

Coding · rahul7star

Q8\_0Excellent

1.5 GB9% of RAM~92 tok/sEstimated0.87B params

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

[NEXUS Medical](/fit/fableforge-ai-nexus-medical?chip=m6&ram=16)

General · fableforge-ai · 2026-07-05

Q8\_0Excellent

2.2 GB14% of RAM~52 tok/sEstimated1.54B params

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

[Nemotron 3 Nano Omni 30B A3B JANGTQ4](/fit/osaurusai-nemotron-3-nano-omni-30b-a3b-jangtq4?chip=m6&ram=16)

General · osaurusai

Q8\_0Excellent

6.9 GB43% of RAMBenchmark needed5.75B params

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

[LLAMA 3.2 1B OpenHermes2.5](/fit/artificialguybr-llama-3-2-1b-openhermes2-5?chip=m6&ram=16)

General · artificialguybr

Q8\_0Excellent

1.9 GB12% of RAM~65 tok/sEstimated1.24B params

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

[Dayhoff 170m GR](/fit/microsoft-dayhoff-170m-gr?chip=m6&ram=16)

General · Microsoft

Q8\_0Excellent

0.7 GB4% of RAMBenchmark needed0.17B params

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

[Dayhoff 170m UR90](/fit/microsoft-dayhoff-170m-ur90?chip=m6&ram=16)

General · Microsoft

Q8\_0Excellent

0.7 GB4% of RAMBenchmark needed0.17B params

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

[Hunyuan 0.5B Pretrain](/fit/tencent-hunyuan-0-5b-pretrain?chip=m6&ram=16)

General · tencent

Q8\_0Excellent

1.1 GB7% of RAM~148 tok/sEstimated0.54B params

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

[GLM 0.5B](/fit/primeintellect-glm-0-5b?chip=m6&ram=16)

General · primeintellect

Q8\_0Excellent

1.1 GB7% of RAMBenchmark needed0.54B params

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

[Qemma Q14B](/fit/reaperdoesntknow-qemma-q14b?chip=m6&ram=16)

General · reaperdoesntknow

Q8\_0Excellent

1.6 GB10% of RAM~79 tok/sEstimated1.01B params

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

[tiny 38m](/fit/darthcrawl-tiny-38m?chip=m6&ram=16)

General · darthcrawl · 2026-05-07

Q8\_0Excellent

0.5 GB3% of RAM~2,004 tok/sEstimated0.04B params

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

[palmer 005](/fit/appvoid-palmer-005?chip=m6&ram=16)

General · appvoid

Q8\_0Excellent

0.6 GB4% of RAM~890 tok/sEstimated0.09B params

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

[fijik 2.0 350m sft](/fit/pinkstack-fijik-2-0-350m-sft?chip=m6&ram=16)

General · pinkstack

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2.5 Encoder 350M Diffusion](/fit/liquidai-lfm2-5-encoder-350m-diffusion?chip=m6&ram=16)

Coding · Liquid AI

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[claude oss 350m](/fit/squ11z1-claude-oss-350m?chip=m6&ram=16)

General · squ11z1

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[Kali Terminus v2](/fit/iselabvn-kali-terminus-v2?chip=m6&ram=16)

General · iselabvn

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[meddies pii](/fit/meddies-meddies-pii?chip=m6&ram=16)

General · meddies

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2.5 350M heretic](/fit/mihaipopa-1-lfm2-5-350m-heretic?chip=m6&ram=16)

General · mihaipopa-1

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[lfm2.5 350m frontend agent](/fit/lazos-lfm2-5-350m-frontend-agent?chip=m6&ram=16)

General · lazos

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[LFM2.5 350M PT zh\_CN](/fit/q1ngmang-lfm2-5-350m-pt-zh_cn?chip=m6&ram=16)

General · q1ngmang

Q8\_0Excellent

0.9 GB6% of RAM~229 tok/sEstimated0.35B params

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

[ERNIE 4.5 0.3B Paddle](/fit/baidu-ernie-4-5-0-3b-paddle?chip=m6&ram=16)

General · baidu

Q8\_0Excellent

0.9 GB6% of RAM~223 tok/sEstimated0.36B params

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

[LFM2.5 VL 450M Extract](/fit/liquidai-lfm2-5-vl-450m-extract?chip=m6&ram=16)

Multimodal · Liquid AI

Q8\_0Excellent

1.0 GB6% of RAM~178 tok/sEstimated0.45B params

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

[Falcon H1 Tiny R 0.6B pre GRPO](/fit/tiiuae-falcon-h1-tiny-r-0-6b-pre-grpo?chip=m6&ram=16)

General · TII

Q8\_0Excellent

1.2 GB7% of RAM~129 tok/sEstimated0.62B params

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

[turkish pii guard 0.8b](/fit/melikegks-turkish-pii-guard-0-8b?chip=m6&ram=16)

General · melikegks

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[Rice Cracker Qwen3.5 0.8B Abliterated Base](/fit/dalatexcoder-rice-cracker-qwen3-5-0-8b-abliterated-base?chip=m6&ram=16)

Coding · dalatexcoder

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[reasoning summarizer 800m pre](/fit/supralabs-reasoning-summarizer-800m-pre?chip=m6&ram=16)

Reasoning · supralabs

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[Kali Terminus v3](/fit/iselabvn-kali-terminus-v3?chip=m6&ram=16)

General · iselabvn

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[Verus 0.8B](/fit/8f-ai-verus-0-8b?chip=m6&ram=16)

Multimodal · 8f-ai

Q8\_0Excellent

1.3 GB8% of RAM~107 tok/sEstimated0.75B params

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

[Phi 3.5 MoE 0.8B A0.2B](/fit/kylesayrs-phi-3-5-moe-0-8b-a0-2b?chip=m6&ram=16)

General · kylesayrs

Q8\_0Excellent

1.4 GB9% of RAMBenchmark needed0.8B params

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

[GLM 5.2 0.8B A0.8B](/fit/inference-optimization-glm-5-2-0-8b-a0-8b?chip=m6&ram=16)

General · inference-optimization

Q8\_0Excellent

1.4 GB9% of RAMBenchmark needed0.85B params

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

[BooruNL 0.8B](/fit/cooperdk-boorunl-0-8b?chip=m6&ram=16)

General · cooperdk

Q8\_0Excellent

1.4 GB9% of RAM~94 tok/sEstimated0.85B params

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

[Qwen3.5 0.8B heretic](/fit/dingdust-qwen3-5-0-8b-heretic?chip=m6&ram=16)

Multimodal · dingdust

Q8\_0Excellent

1.4 GB9% of RAM~94 tok/sEstimated0.85B params

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

[ProCIR](/fit/yuandaxia-procir?chip=m6&ram=16)

Multimodal · yuandaxia

Q8\_0Excellent

1.4 GB9% of RAM~94 tok/sEstimated0.85B params

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

[MiniCPM5 1B heretic](/fit/dingdust-minicpm5-1b-heretic?chip=m6&ram=16)

General · dingdust

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[MiniCPM5 1B SFT Fable5](/fit/ermiaazarkhalili-minicpm5-1b-sft-fable5?chip=m6&ram=16)

General · ermiaazarkhalili

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[minicpm5 1b kids storyteller](/fit/thepradip-minicpm5-1b-kids-storyteller?chip=m6&ram=16)

General · thepradip

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[MiniCPM5 1B PTBR v5](/fit/marinarosa-minicpm5-1b-ptbr-v5?chip=m6&ram=16)

General · marinarosa

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[minicpm5 1b vivamais v0](/fit/marinarosa-minicpm5-1b-vivamais-v0?chip=m6&ram=16)

General · marinarosa

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[Prompt Refine MiniCPM5 1B](/fit/ephemeralyou-prompt-refine-minicpm5-1b?chip=m6&ram=16)

General · ephemeralyou

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[minicpm5 1b vivamais v1](/fit/marinarosa-minicpm5-1b-vivamais-v1?chip=m6&ram=16)

General · marinarosa

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[minicpm5 1b vivamais v2](/fit/marinarosa-minicpm5-1b-vivamais-v2?chip=m6&ram=16)

General · marinarosa

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[minicpm5 stock analyst v2 mtp](/fit/ewinregirgojr-minicpm5-stock-analyst-v2-mtp?chip=m6&ram=16)

General · ewinregirgojr

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

[MiniCPM5 1B Reasoning Agent Ultra](/fit/healshsj-minicpm5-1b-reasoning-agent-ultra?chip=m6&ram=16)

Reasoning · healshsj

Q8\_0Excellent

1.7 GB11% of RAM~74 tok/sEstimated1.08B params

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

Show more (6413 remaining)

## Measured on the M6

Nobody has submitted a benchmark on the M6 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 mini M4

29% less memory bandwidth

](/mac-mini/m4)

## 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 M6's 170 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 32 GB machine can hand almost all of that to a model with no copy across a bus.

The mini is the cheapest way onto this chip, and it runs headless on a shelf perfectly well. Nothing about local inference needs the display attached. 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 M6 Mac mini run a 70B model?

No. A 70B model at Q4\_K\_M needs about 46 GB, and the largest M6 Mac mini tops out at 32 GB, which leaves about 28 GB for weights. The practical ceiling on this machine is around 42B parameters at Q4.

### How much unified memory should I get with the M6 Mac mini?

Memory is the only spec that changes what you can run at all. 16 GB holds about a 20B model at Q4; 32 GB holds about 42B. 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 M6?

Token generation is bandwidth-bound, so M6 throughput scales with its 170 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 M6 lands in the tens of tokens per second and a 70B model lands in the single digits.

### Should I buy the M6 Mac mini 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 M6 already holds about a 42B model at Q4. If your target model fits in 32 GB, waiting buys throughput rather than capability.

## Run these models on your Mac mini

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=m6&ram=16)

[![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.