---
title: "MacBook Pro 14\" M3 Max: What AI Models Can It Run? | ModelPiper"
description: "Local AI on the M3 Max MacBook Pro 14\": 300 to 400 GB/s memory bandwidth and 36 to 128 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run."
canonical: "https://modelpiper.com/macbook-pro-14/m3-max"
---

# MacBook Pro 14" M3 Max: What AI Models Can It Run? | ModelPiper

> Local AI on the M3 Max MacBook Pro 14": 300 to 400 GB/s memory bandwidth and 36 to 128 GB of unified memory. See which LLMs fit, at which quantization, and how fast they run.

[← All MacBook Pro 14" models](/macbook-pro-14)

# MacBook Pro 14" M3 Max

The M3 Max MacBook Pro 14" runs local models at 300 to 400 GB/s of memory bandwidth with 36 to 128 GB of unified memory. On Apple Silicon that memory is shared with the GPU, so the whole pool is available for weights: at 128 GB you can hold roughly a 172B dense model at Q4. The Max is where the bus gets wide enough that model size, not bandwidth, becomes the thing you plan around.

Apple no longer sells this configuration new. It stays fully evaluated here because the used market is where most of its local AI value now sits.

## Specifications

ChipApple M3 Max

CPU cores14 or 16

GPU cores30 or 40

Unified memory36, 48, 64, 96, or 128 GB

Memory bandwidth300 to 400 GB/s

Neural Engine18 TOPS

Released2023

AvailabilityUsed market

Memory bandwidth is faster than 56% of the Apple Silicon chips shipped in a Mac, against a 819 GB/s peak.

Its memory ceiling is above 67% 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

30-core 300 GB/s 40-core 400 GB/s

Unified memory

36 GB96 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.

[36 GB](#ram-36gb)[48 GB](#ram-48gb)[64 GB](#ram-64gb)[96 GB](#ram-96gb)[128 GB](#ram-128gb)

### 36 GB unified memory

31 GB usable for weights · 300 GB/s

3,417 of 3,641 models fit, and 3,252 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Chinese Mixtral 8x7B](/fit/hit-scir-chinese-mixtral-8x7b) · 46.91B

Best all-round pick

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b) · Q8\_0 · ~181 tok/s

### 48 GB unified memory

42 GB usable for weights · 400 GB/s

3,503 of 3,641 models fit, and 3,351 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Yi 34Bx2 MoE 60B DPO](/fit/cloudyu-yi-34bx2-moe-60b-dpo) · 60.81B

Best all-round pick

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b) · Q8\_0 · ~241 tok/s

### 64 GB unified memory

56 GB usable for weights · 400 GB/s

3,541 of 3,641 models fit, and 3,385 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Kimi K2.6 JANGTQ\_3L](/fit/deviad-kimi-k2-6-jangtq_3l) · 83.44B

Best all-round pick

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b) · Q8\_0 · ~241 tok/s

### 96 GB unified memory

84 GB usable for weights · 300 GB/s

3,556 of 3,641 models fit, and 3,503 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Qwen3.5 122B A10B](/fit/qwen-qwen3-5-122b-a10b) · 125.09B

Best all-round pick

[Qwen3.6 35B A3B](/fit/qwen-qwen3-6-35b-a3b) · Q8\_0 · ~52 tok/s

### 128 GB unified memory

112 GB usable for weights · 400 GB/s

3,582 of 3,641 models fit, and 3,532 of them run with headroom rather than as a squeeze.

Largest model at Q4

[Kimi K2.5](/fit/moonshotai-kimi-k2-5) · 171B

Best all-round pick

[Qwen3.6 35B A3B](/fit/qwen-qwen3-6-35b-a3b) · Q8\_0 · ~70 tok/s

## What a 36 GB M3 Max MacBook Pro 14" can run

Every model in the database against this exact configuration, at 300 GB/s. Ratings and speeds are the same numbers the model pages show.

All Categories

Show All

All Sizes

Best Fit

Showing 3641 of 3641 models

[Qwen3.5 0.8B](/fit/qwen-qwen3-5-0-8b)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB4% of RAM~181 tok/sEstimated0.87B params

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

[Qwen3.5 2B](/fit/qwen-qwen3-5-2b)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB8% of RAM~69 tok/sEstimated2.27B params

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

[Qwen3.5 0.8B Base](/fit/qwen-qwen3-5-0-8b-base)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

1.5 GB4% of RAM~181 tok/sEstimated0.87B params

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

[Qwen3.5 2B Base](/fit/qwen-qwen3-5-2b-base)

Multimodal · Alibaba · 2026-02-28

Q8\_0Excellent

3.0 GB8% of RAM~69 tok/sEstimated2.27B params

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

[Qwen3.5 4B](/fit/qwen-qwen3-5-4b)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

5.7 GB16% of RAM~34 tok/sEstimated4.66B params

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

[Qwen3.5 4B Base](/fit/qwen-qwen3-5-4b-base)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

5.7 GB16% of RAM~34 tok/sEstimated4.66B params

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

[LFM2 1.2B](/fit/liquidai-lfm2-1-2b)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 ColBERT 350M](/fit/liquidai-lfm2-colbert-350m)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[LFM2.5 1.2B Thinking](/fit/liquidai-lfm2-5-1-2b-thinking)

Reasoning · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 8B A1B](/fit/liquidai-lfm2-8b-a1b)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

9.8 GB27% of RAMBenchmark needed8.3B params

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

[LFM2.5 1.2B Base](/fit/liquidai-lfm2-5-1-2b-base)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 350M](/fit/liquidai-lfm2-350m)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[LFM2 2.6B](/fit/liquidai-lfm2-2-6b)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

3.4 GB9% of RAM~61 tok/sEstimated2.57B params

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

[LFM2 700M](/fit/liquidai-lfm2-700m)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.3 GB4% of RAM~212 tok/sEstimated0.74B params

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

[LFM2 1.2B Extract](/fit/liquidai-lfm2-1-2b-extract)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 350M Extract](/fit/liquidai-lfm2-350m-extract)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[LFM2 2.6B Transcript](/fit/liquidai-lfm2-2-6b-transcript)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

3.4 GB9% of RAM~61 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)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[LFM2 1.2B Tool](/fit/liquidai-lfm2-1-2b-tool)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 350M ENJP MT](/fit/liquidai-lfm2-350m-enjp-mt)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[LFM2 1.2B RAG](/fit/liquidai-lfm2-1-2b-rag)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 350M Math](/fit/liquidai-lfm2-350m-math)

Reasoning · Liquid AI · 2025-11-28

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[granite 4.0 h tiny](/fit/ibm-granite-granite-4-0-h-tiny)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

8.2 GB23% of RAMBenchmark needed6.94B params

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

[LFM2.5 1.2B Instruct](/fit/liquidai-lfm2-5-1-2b-instruct)

Chat · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[LFM2 2.6B Exp](/fit/liquidai-lfm2-2-6b-exp)

Chat · Liquid AI · 2025-11-28

Q8\_0Excellent

3.4 GB9% of RAM~61 tok/sEstimated2.57B params

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

[LFM2.5 1.2B JP](/fit/liquidai-lfm2-5-1-2b-jp)

Chat · Liquid AI · 2025-11-28

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[VAETKI 7B A1B](/fit/nc-ai-consortium-vaetki-7b-a1b)

General · NCAI · 2025-12-29

Q8\_0Excellent

8.6 GB24% of RAMBenchmark needed7.25B params

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

[SmolLM3 3B](/fit/huggingfacetb-smollm3-3b)

Reasoning · HuggingFace · 2025-07-08

Q8\_0Excellent

3.8 GB11% of RAM~52 tok/sEstimated3B params

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

[granite 4.0 h micro](/fit/ibm-granite-granite-4-0-h-micro)

General · ibm-granite · 2025-09-16

Q8\_0Excellent

4.1 GB11% of RAM~49 tok/sEstimated3.19B params

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

[LFM2.5 Audio 1.5B](/fit/liquidai-lfm2-5-audio-1-5b)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[LFM2 Audio 1.5B](/fit/liquidai-lfm2-audio-1-5b)

General · Liquid AI · 2025-11-28

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[VAETKI VL 7B A1B](/fit/nc-ai-consortium-vaetki-vl-7b-a1b)

Multimodal · NCAI · 2025-12-29

Q8\_0Excellent

9.0 GB25% of RAMBenchmark needed7.58B params

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

[gemma 4 E2B it](/fit/google-gemma-4-e2b-it)

Multimodal · Google · 2025-07-30

Q8\_0Excellent

6.2 GB17% of RAM~31 tok/sEstimated5.1B params

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

[gemma 3n E2B it](/fit/google-gemma-3n-e2b-it)

Multimodal · Google · 2025-06-25

Q8\_0Excellent

5.0 GB14% of RAM~39 tok/sEstimated4B params

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

[LFM2 VL 450M](/fit/liquidai-lfm2-vl-450m)

Multimodal · Liquid AI · 2025-11-28

Q8\_0Excellent

1.0 GB3% of RAM~349 tok/sEstimated0.45B params

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

[LFM2.5 VL 1.6B](/fit/liquidai-lfm2-5-vl-1-6b)

Multimodal · Liquid AI · 2025-11-28

Q8\_0Excellent

2.3 GB6% of RAM~98 tok/sEstimated1.6B params

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

[LFM2 VL 3B](/fit/liquidai-lfm2-vl-3b)

Multimodal · Liquid AI · 2025-11-28

Q8\_0Excellent

3.8 GB11% of RAM~52 tok/sEstimated3B params

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

[LFM2 VL 1.6B](/fit/liquidai-lfm2-vl-1-6b)

Multimodal · Liquid AI · 2025-11-28

Q8\_0Excellent

2.3 GB6% of RAM~99 tok/sEstimated1.58B 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)

Reasoning · jackrong · 2026-03-16

Q8\_0Excellent

11.3 GB31% of RAM~16 tok/sEstimated9.65B params

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

[EXAONE Deep 2.4B](/fit/lgai-exaone-exaone-deep-2-4b)

General · lgai-exaone · 2025-03-12

Q8\_0Excellent

3.2 GB9% of RAM~65 tok/sEstimated2.41B params

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

[EXAONE 4.0 1.2B](/fit/lgai-exaone-exaone-4-0-1-2b)

General · LG AI · 2025-07-15

Q8\_0Excellent

1.8 GB5% of RAM~131 tok/sEstimated1.2B params

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

[Jolia](/fit/raidium-jolia)

General · raidium · 2026-06-15

Q8\_0Excellent

0.5 GB1% of RAM~7,857 tok/sEstimated0.02B params

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

[VAETKI 20B A2B](/fit/nc-ai-consortium-vaetki-20b-a2b)

General · NCAI · 2025-12-29

Q8\_0Excellent

22.4 GB62% of RAMBenchmark needed19.6B params

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

[embeddinggemma GTAIDE 300m 2605](/fit/taide-embeddinggemma-gtaide-300m-2605)

Embedding · taide · 2026-06-12

Q8\_0Excellent

0.8 GB2% of RAM~524 tok/sEstimated0.3B params

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

[Qwen3 0.6B](/fit/qwen-qwen3-0-6b)

General · Alibaba · 2025-04-27

Q8\_0Excellent

1.3 GB4% of RAM~210 tok/sEstimated0.75B params

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

[Qwen3 1.7B](/fit/qwen-qwen3-1-7b)

General · Alibaba · 2025-04-27

Q8\_0Excellent

2.8 GB8% of RAM~77 tok/sEstimated2.03B params

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

[GLM OCR](/fit/zai-org-glm-ocr)

Multimodal · zai-org

Q8\_0Excellent

2.0 GB6% of RAM~118 tok/sEstimated1.33B params

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

[Qwen3 VL 2B Instruct](/fit/qwen-qwen3-vl-2b-instruct)

Multimodal · Alibaba

Q8\_0Excellent

2.9 GB8% of RAM~74 tok/sEstimated2.13B params

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

[Qwen2.5 1.5B](/fit/qwen-qwen2-5-1-5b)

General · Alibaba

Q8\_0Excellent

2.2 GB6% of RAM~102 tok/sEstimated1.54B params

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

[Qwen2 0.5B](/fit/qwen-qwen2-0-5b)

General · Alibaba

Q8\_0Excellent

1.0 GB3% of RAM~321 tok/sEstimated0.49B params

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

[MiniCPM V 4.6](/fit/openbmb-minicpm-v-4-6)

Multimodal · openbmb

Q8\_0Excellent

2.0 GB5% of RAM~121 tok/sEstimated1.3B 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)

Reasoning · DeepSeek

Q8\_0Excellent

2.5 GB7% of RAM~88 tok/sEstimated1.78B params

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

[dots.mocr](/fit/rednote-hilab-dots-mocr)

Multimodal · rednote-hilab

Q8\_0Excellent

3.9 GB11% of RAM~52 tok/sEstimated3.04B params

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

[DeepSeek V2 Lite](/fit/deepseek-ai-deepseek-v2-lite)

General · DeepSeek

Q8\_0Excellent

18.0 GB50% of RAMBenchmark needed15.71B params

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

[surya ocr 2](/fit/datalab-to-surya-ocr-2)

Multimodal · datalab-to

Q8\_0Excellent

1.3 GB4% of RAM~228 tok/sEstimated0.69B params

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

[Kimi VL A3B Instruct](/fit/moonshotai-kimi-vl-a3b-instruct)

Multimodal · moonshotai

Q8\_0Excellent

18.8 GB52% of RAMBenchmark needed16.41B params

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

[MiniCPM5 1B](/fit/openbmb-minicpm5-1b)

General · openbmb

Q8\_0Excellent

1.7 GB5% of RAM~146 tok/sEstimated1.08B params

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

[dots.ocr](/fit/rednote-hilab-dots-ocr)

Multimodal · rednote-hilab

Q8\_0Excellent

3.9 GB11% of RAM~52 tok/sEstimated3.04B params

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

[Ilama 3.2 1B](/fit/hmellor-ilama-3-2-1b)

General · hmellor

Q8\_0Excellent

1.9 GB5% of RAM~127 tok/sEstimated1.24B params

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

[distil lfm25 shellper](/fit/distil-labs-distil-lfm25-shellper)

General · distil-labs

Q8\_0Excellent

0.9 GB2% of RAM~449 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)

General · farbodtavakkoli

Q8\_0Excellent

1.8 GB5% of RAM~130 tok/sEstimated1.21B params

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

[LFM2.5 8B A1B](/fit/liquidai-lfm2-5-8b-a1b)

General · Liquid AI

Q8\_0Excellent

9.9 GB28% of RAMBenchmark needed8.47B params

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

[granite 4.0 tiny preview](/fit/ibm-granite-granite-4-0-tiny-preview)

General · ibm-granite

Q8\_0Excellent

7.9 GB22% of RAMBenchmark needed6.67B params

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

[reformer crime and punishment](/fit/google-reformer-crime-and-punishment)

General · Google

Q8\_0Excellent

0.5 GB1% of RAM~15,714 tok/sEstimated0.01B params

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

[Kimi VL A3B Thinking](/fit/moonshotai-kimi-vl-a3b-thinking)

Multimodal · moonshotai

Q8\_0Excellent

18.8 GB52% of RAMBenchmark needed16.41B params

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

[VideoLLaMA3 2B Image HF](/fit/lkhl-videollama3-2b-image-hf)

Multimodal · lkhl

Q8\_0Excellent

2.7 GB7% of RAM~80 tok/sEstimated1.96B params

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

[ReaderLM v2](/fit/jinaai-readerlm-v2)

General · jinaai

Q8\_0Excellent

2.2 GB6% of RAM~102 tok/sEstimated1.54B params

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

[Qwen3 VL 2B Thinking](/fit/qwen-qwen3-vl-2b-thinking)

General · Alibaba

Q8\_0Excellent

2.9 GB8% of RAM~74 tok/sEstimated2.13B params

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

[typhoon ocr1.5 2b](/fit/typhoon-ai-typhoon-ocr1-5-2b)

Reasoning · typhoon-ai

Q8\_0Excellent

2.9 GB8% of RAM~74 tok/sEstimated2.13B params

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

[Solar Open 100B](/fit/upstage-solar-open-100b)

General · Upstage

Q8\_0Excellent

9.5 GB26% of RAMBenchmark needed8.05B params

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

[gpt oss safeguard 120b](/fit/openai-gpt-oss-safeguard-120b)

General · openai

Q8\_0Excellent

3.1 GB9% of RAMBenchmark needed2.37B params

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

[PaddleOCR VL 1.5](/fit/paddlepaddle-paddleocr-vl-1-5)

General · paddlepaddle

Q8\_0Excellent

1.6 GB4% of RAM~164 tok/sEstimated0.96B params

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

[LFM2.5 350M Base](/fit/liquidai-lfm2-5-350m-base)

General · Liquid AI

Q8\_0Excellent

0.9 GB2% of RAM~449 tok/sEstimated0.35B params

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

[plamo 2 1b](/fit/pfnet-plamo-2-1b)

General · pfnet

Q8\_0Excellent

1.9 GB5% of RAM~122 tok/sEstimated1.29B params

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

[MiniCPM5 1B SFT](/fit/openbmb-minicpm5-1b-sft)

General · openbmb

Q8\_0Excellent

1.7 GB5% of RAM~146 tok/sEstimated1.08B params

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

[ERNIE 4.5 0.3B PT](/fit/baidu-ernie-4-5-0-3b-pt)

General · baidu

Q8\_0Excellent

0.9 GB3% of RAM~437 tok/sEstimated0.36B params

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

[Mellum2 12B A2.5B Thinking](/fit/jetbrains-mellum2-12b-a2-5b-thinking)

General · jetbrains

Q8\_0Excellent

14.1 GB39% of RAMBenchmark needed12.15B params

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

[PARD Llama 3.2 1B](/fit/amd-pard-llama-3-2-1b)

General · amd

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[academic ds 9B](/fit/bytedance-seed-academic-ds-9b)

General · bytedance-seed

Q8\_0Excellent

11.0 GB30% of RAMBenchmark needed9.37B params

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

[Trinity Nano Preview](/fit/arcee-ai-trinity-nano-preview)

General · arcee-ai

Q8\_0Excellent

7.3 GB20% of RAMBenchmark needed6.12B params

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

[Orpo Llama 3.2 1B 15k](/fit/adamlucek-orpo-llama-3-2-1b-15k)

General · adamlucek

Q8\_0Excellent

1.9 GB5% of RAM~127 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)

Coding · shahriarferdoush

Q8\_0Excellent

1.9 GB5% of RAM~127 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)

General · ahczhg

Q8\_0Excellent

1.9 GB5% of RAM~127 tok/sEstimated1.24B params

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

[CyberXP\_Agent\_Llama\_3.2\_1B](/fit/abaryan-cyberxp_agent_llama_3-2_1b)

General · abaryan

Q8\_0Excellent

1.9 GB5% of RAM~127 tok/sEstimated1.24B params

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

[Tashkeel 700M](/fit/etherll-tashkeel-700m)

General · etherll

Q8\_0Excellent

1.3 GB4% of RAM~212 tok/sEstimated0.74B params

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

[Mellum2 12B A2.5B Base](/fit/jetbrains-mellum2-12b-a2-5b-base)

General · jetbrains

Q8\_0Excellent

14.1 GB39% of RAMBenchmark needed12.15B params

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

[OTel LLM 20B IT](/fit/farbodtavakkoli-otel-llm-20b-it)

General · farbodtavakkoli

Q8\_0Excellent

2.5 GB7% of RAMBenchmark needed1.77B params

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

[Qwen3 4B Kimi2.5 Reasoning Distilled](/fit/khazarai-qwen3-4b-kimi2-5-reasoning-distilled-gguf)

Reasoning · khazarai

Q8\_0Excellent

4.0 GB11% of RAM~50 tok/sEstimated3.13B params

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

[FastVLM 0.5B](/fit/kamilamila-fastvlm-0-5b)

General · kamilamila

Q8\_0Excellent

1.2 GB3% of RAM~253 tok/sEstimated0.62B params

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

[transcription cleanup llama3.2 1b](/fit/getonit-transcription-cleanup-llama3-2-1b)

General · getonit

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[PaddleOCR VL](/fit/paddlepaddle-paddleocr-vl)

General · paddlepaddle

Q8\_0Excellent

1.6 GB4% of RAM~164 tok/sEstimated0.96B params

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

[Kimi VL A3B Thinking 2506](/fit/moonshotai-kimi-vl-a3b-thinking-2506)

General · moonshotai

Q8\_0Excellent

18.8 GB52% of RAMBenchmark needed16.41B params

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

[MiniMax M2.7 JANGTQ](/fit/jangq-ai-minimax-m2-7-jangtq)

General · jangq-ai

Q8\_0Excellent

17.6 GB49% of RAMBenchmark needed15.3B params

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

[DeepScaleR 1.5B Preview](/fit/agentica-org-deepscaler-1-5b-preview)

General · agentica-org

Q8\_0Excellent

2.5 GB7% of RAM~88 tok/sEstimated1.78B params

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

[SEX\_ROLEPLAY 3.2 1B](/fit/novaciano-sex_roleplay-3-2-1b)

General · novaciano

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[Qwen3 VL 2B RRG SFT](/fit/dmusingu-qwen3-vl-2b-rrg-sft)

General · dmusingu

Q8\_0Excellent

2.9 GB8% of RAM~74 tok/sEstimated2.13B params

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

[JiRackTernary\_1b](/fit/kgrabko-jirackternary_1b)

General · kgrabko

Q8\_0Excellent

2.2 GB6% of RAM~105 tok/sEstimated1.5B params

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

[LFM2.5 350M home assistant sft](/fit/ordenwills-lfm2-5-350m-home-assistant-sft)

General · ordenwills

Q8\_0Excellent

0.9 GB2% of RAM~449 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)

General · smcleish

Q8\_0Excellent

2.1 GB6% of RAM~113 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)

General · carsenk

Q8\_0Excellent

1.9 GB5% of RAM~127 tok/sEstimated1.24B params

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

[MiniMax M2.7 JANGTQ CRACK](/fit/dealignai-minimax-m2-7-jangtq-crack)

General · dealignai

Q8\_0Excellent

17.6 GB49% of RAMBenchmark needed15.3B params

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

[OpenReasoning Nemotron 1.5B](/fit/nvidia-openreasoning-nemotron-1-5b)

Reasoning · nvidia

Q8\_0Excellent

2.2 GB6% of RAM~102 tok/sEstimated1.54B params

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

[Miss MARTHA hot POCKET edition 2B OMNI](/fit/zero-point-ai-miss-martha-hot-pocket-edition-2b-omni)

General · zero-point-ai

Q8\_0Excellent

3.0 GB8% of RAM~69 tok/sEstimated2.27B params

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

[Gravity 16B A3B Preview](/fit/trillionlabs-gravity-16b-a3b-preview)

General · trillionlabs

Q8\_0Excellent

18.6 GB52% of RAMBenchmark needed16.24B params

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

[Nemotron 3 Super 120B A12B UNCENSORED JANG\_2L](/fit/dealignai-nemotron-3-super-120b-a12b-uncensored-jang_2l)

General · dealignai

Q8\_0Excellent

14.5 GB40% of RAMBenchmark needed12.59B params

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

[granite 3.1 1b a400m base](/fit/ibm-granite-granite-3-1-1b-a400m-base)

General · ibm-granite

Q8\_0Excellent

2.0 GB6% of RAMBenchmark needed1.33B params

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

[MiniCPM V 4.6 Thinking](/fit/openbmb-minicpm-v-4-6-thinking)

General · openbmb

Q8\_0Excellent

2.0 GB5% of RAM~121 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)

General · ibm-granite

Q8\_0Excellent

2.1 GB6% of RAM~108 tok/sEstimated1.46B params

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

[MiniMax M2.7 Small JANGTQ](/fit/osaurusai-minimax-m2-7-small-jangtq)

General · osaurusai

Q8\_0Excellent

11.3 GB31% of RAMBenchmark needed9.65B params

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

[gpt oss 120b lora merged redux](/fit/pyoakum-gpt-oss-120b-lora-merged-redux)

General · pyoakum

Q8\_0Excellent

6.5 GB18% 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)

General · ibm-granite

Q8\_0Excellent

4.2 GB12% 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)

General · treadon

Q8\_0Excellent

2.0 GB5% of RAM~121 tok/sEstimated1.3B params

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

[Youtu LLM 2B](/fit/tencent-youtu-llm-2b)

General · tencent

Q8\_0Excellent

2.7 GB7% of RAM~80 tok/sEstimated1.96B params

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

[DeepSeek Coder V2 Lite Base](/fit/deepseek-ai-deepseek-coder-v2-lite-base)

Coding · DeepSeek

Q8\_0Excellent

18.0 GB50% of RAMBenchmark needed15.71B params

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

[ODIN C1](/fit/skis-ai-research-odin-c1)

General · skis-ai-research

Q8\_0Excellent

1.8 GB5% of RAM~134 tok/sEstimated1.17B params

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

[Lucy 128k](/fit/menlo-lucy-128k)

General · menlo

Q8\_0Excellent

2.4 GB7% of RAM~91 tok/sEstimated1.72B params

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

[llama3.2\_1B\_vl](/fit/thkim0305-llama3-2_1b_vl)

General · thkim0305

Q8\_0Excellent

1.6 GB4% of RAM~157 tok/sEstimated1B params

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

[veridian beta](/fit/magistrtheone-veridian-beta)

General · magistrtheone

Q8\_0Excellent

11.5 GB32% of RAMBenchmark needed9.87B 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)

Reasoning · jackrong

Q8\_0Excellent

1.5 GB4% of RAM~181 tok/sEstimated0.87B params

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

[Huihui Qwen3.5 2B abliterated](/fit/huihui-ai-huihui-qwen3-5-2b-abliterated)

General · huihui-ai

Q8\_0Excellent

3.0 GB8% of RAM~69 tok/sEstimated2.27B 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)

Coding · rahul7star

Q8\_0Excellent

1.5 GB4% of RAM~181 tok/sEstimated0.87B params

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

[UI Venus 1.5 2B](/fit/inclusionai-ui-venus-1-5-2b)

General · inclusionai

Q8\_0Excellent

3.2 GB9% of RAM~64 tok/sEstimated2.44B params

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

[Falcon H1 1.5B Base](/fit/tiiuae-falcon-h1-1-5b-base)

General · TII

Q8\_0Excellent

2.2 GB6% of RAM~101 tok/sEstimated1.55B params

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

[Qwen3 Coder Next DFlash](/fit/z-lab-qwen3-coder-next-dflash)

Coding · z-lab

Q8\_0Excellent

1.7 GB5% of RAM~146 tok/sEstimated1.08B 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)

General · osaurusai

Q8\_0Excellent

6.9 GB19% 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)

General · artificialguybr

Q8\_0Excellent

1.9 GB5% of RAM~127 tok/sEstimated1.24B params

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

[Dayhoff 170m GR](/fit/microsoft-dayhoff-170m-gr)

General · Microsoft

Q8\_0Excellent

0.7 GB2% of RAMBenchmark needed0.17B params

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

[evolai qwen2.5 1.5b](/fit/roystar-evolai-qwen2-5-1-5b)

General · roystar

Q8\_0Excellent

2.2 GB6% of RAM~102 tok/sEstimated1.54B params

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

[VibeThinker 1.5B](/fit/weiboai-vibethinker-1-5b)

General · weiboai

Q8\_0Excellent

2.5 GB7% of RAM~88 tok/sEstimated1.78B params

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

[Dayhoff 170m UR90](/fit/microsoft-dayhoff-170m-ur90)

General · Microsoft

Q8\_0Excellent

0.7 GB2% of RAMBenchmark needed0.17B params

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

[AI21 Jamba Reasoning 3B](/fit/ai21labs-ai21-jamba-reasoning-3b)

Reasoning · ai21labs

Q8\_0Excellent

4.1 GB11% of RAMBenchmark needed3.2B params

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

[Falcon H1 1.5B Deep Base](/fit/tiiuae-falcon-h1-1-5b-deep-base)

General · TII

Q8\_0Excellent

2.2 GB6% of RAM~101 tok/sEstimated1.55B params

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

[Hunyuan 0.5B Pretrain](/fit/tencent-hunyuan-0-5b-pretrain)

General · tencent

Q8\_0Excellent

1.1 GB3% of RAM~291 tok/sEstimated0.54B params

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

[GLM 0.5B](/fit/primeintellect-glm-0-5b)

General · primeintellect

Q8\_0Excellent

1.1 GB3% of RAMBenchmark needed0.54B params

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

[Qwen3.5 9B](/fit/qwen-qwen3-5-9b)

Multimodal · Alibaba · 2026-02-27

Q8\_0Excellent

11.3 GB31% of RAM~16 tok/sEstimated9.65B params

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

[Qwen3 VL 4B Instruct](/fit/qwen-qwen3-vl-4b-instruct)

Multimodal · Alibaba

Q8\_0Excellent

5.5 GB15% of RAM~35 tok/sEstimated4.44B params

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

[gemma 4 12b it](/fit/google-gemma-4-12b-it)

Multimodal · google · 2026-05

Q8\_0Excellent

13.8 GB38% of RAM~13 tok/sEstimated11.96B params

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

[Phi 3.5 vision instruct](/fit/microsoft-phi-3-5-vision-instruct)

Multimodal · Microsoft

Q8\_0Excellent

5.1 GB14% of RAM~38 tok/sEstimated4.15B params

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

[DeepSeek Coder V2 Lite Instruct](/fit/deepseek-ai-deepseek-coder-v2-lite-instruct)

Coding · DeepSeek · 2024-06-14

Q8\_0Excellent

18.0 GB50% of RAMBenchmark needed15.7B params

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

[granite 4.1 3b](/fit/ibm-granite-granite-4-1-3b)

General · ibm-granite

Q8\_0Excellent

4.3 GB12% of RAM~46 tok/sEstimated3.4B params

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

[Nanonets OCR2 3B](/fit/nanonets-nanonets-ocr2-3b)

Multimodal · nanonets

Q8\_0Excellent

4.7 GB13% of RAM~42 tok/sEstimated3.75B params

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

[Qwen3.5 9B Base](/fit/qwen-qwen3-5-9b-base)

Multimodal · Alibaba · 2026-02-26

Q8\_0Excellent

11.3 GB31% of RAM~16 tok/sEstimated9.65B params

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

[granite vision 4.1 4b](/fit/ibm-granite-granite-vision-4-1-4b)

Multimodal · ibm-granite

Q8\_0Excellent

5.0 GB14% of RAM~39 tok/sEstimated4B params

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

[typhoon ocr 3b](/fit/typhoon-ai-typhoon-ocr-3b)

Multimodal · typhoon-ai

Q8\_0Excellent

4.7 GB13% of RAM~42 tok/sEstimated3.75B params

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

[internlm2\_5 step prover critic](/fit/internlm-internlm2_5-step-prover-critic)

General · internlm

Q8\_0Excellent

2.1 GB6% of RAM~112 tok/sEstimated1.4B params

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

[Josiefied Qwen3 VL 4B Instruct abliterated beta v1](/fit/goekdeniz-guelmez-josiefied-qwen3-vl-4b-instruct-abliterated-beta-v1)

Multimodal · goekdeniz-guelmez

Q8\_0Excellent

5.5 GB15% of RAM~35 tok/sEstimated4.44B params

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

[dots.ocr 1.5](/fit/kristaller486-dots-ocr-1-5)

General · kristaller486

Q8\_0Excellent

3.9 GB11% of RAM~52 tok/sEstimated3.04B params

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

[granite 4.1 3b base](/fit/ibm-granite-granite-4-1-3b-base)

General · ibm-granite

Q8\_0Excellent

4.3 GB12% of RAM~46 tok/sEstimated3.4B params

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

[VibeThinker 3B](/fit/weiboai-vibethinker-3b)

General · weiboai

Q8\_0Excellent

3.9 GB11% of RAM~51 tok/sEstimated3.09B params

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

[libra v1.0 3b](/fit/x-izhang-libra-v1-0-3b)

General · x-izhang

Q8\_0Excellent

4.1 GB11% of RAM~48 tok/sEstimated3.25B params

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

Show more (3491 remaining)

## 30-core vs 40-core GPU

Apple ties the memory bus to the bin on this chip: 300 GB/s at 30 cores and 400 GB/s at 40. That moves tokens per second. It does not move which models fit, because that is memory, not cores.

Configuration

Memory bandwidth

Memory options

Models that fit

14-core CPU, 30-core GPU

300 GB/s

36, 96 GB

Identical

16-core CPU, 40-core GPU

400 GB/s

48, 64, 128 GB

Identical

On [openbuddy zero 56b v21.2 32k](/fit/openbuddy-openbuddy-zero-56b-v21-2-32k) the 30-core generates about 8 tok/s and the 40-core about 10 tok/s, a 33% difference. Both hold the model at the same quantization.

## Measured on the M3 Max

Nobody has submitted a benchmark on the M3 Max 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.

[Newer generation

MacBook Pro 14" M5 Max

1.5x the memory bandwidth

](/macbook-pro-14/m5-max)[Used market alternative

MacBook Pro 14" M2 Max

96 GB ceiling instead of 128 GB

](/macbook-pro-14/m2-max)[Same chip, other Mac

MacBook Pro 16" M3 Max

The same chip in a different Mac

](/macbook-pro-16/m3-max)

## 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 M3 Max's 400 GB/s bus is shared by CPU, GPU, and Neural Engine, so a 128 GB machine can hand almost all of that to a model with no copy across a bus.

Apple stopped selling this one, which is exactly why it is interesting. The 14-inch chassis cools well enough to hold its clocks through a long generation run, and it is the smallest machine Apple puts a Max chip in. A used M3 Max at 128 GB still gives you 400 GB/s and a hard 172B ceiling, and neither number degrades with age the way a battery does.

## Common questions

### Can the M3 Max MacBook Pro 14" run a 70B model?

Yes, at 128 GB. A 70B model at Q4\_K\_M needs about 46 GB including an 8K context, and 128 GB of unified memory leaves about 112 GB for weights once macOS takes its share. At 36 GB it does not fit at any quantization worth running.

### How much unified memory should I get with the M3 Max MacBook Pro 14"?

Memory is the only spec that changes what you can run at all. 36 GB holds about a 47B model at Q4; 128 GB holds about 172B. 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 M3 Max?

Token generation is bandwidth-bound, so M3 Max throughput scales with its 400 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 M3 Max lands in the tens of tokens per second and a 70B model lands in the single digits.

### Is the 40-core GPU worth it over the 30-core on the M3 Max?

For throughput, yes: Apple ties bandwidth to the bin here, so the 30-core runs at 300 GB/s and the 40-core at 400 GB/s, about 33% more. For fit, no: both bins hold exactly the same models, because that is set by memory rather than by cores.

### Is a used M3 Max MacBook Pro 14" still worth buying for local AI?

For inference, the specs that matter do not age: 400 GB/s and up to 128 GB of unified memory are the same numbers today as they were in 2023. A used M3 Max at the top memory option usually beats a new base-tier machine at the same price on both. Check the battery and the display, not the silicon.

## Run these models on your MacBook Pro 14"

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=m3-max&ram=36)

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

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.

My Connections

### AI Providers

No providers yet. Click + to add one.

Services

ToolPiper

VisionPiper

AudioPiper