Open-weight models that run on Apple M5 Max (40-core GPU) · 64 GB

Unified memory 64 GB
Bandwidth 614 GB/s
Usable 48.0 GB

Specs: Memory · Mac Studio - Technical Specifications - Apple · Bandwidth · MacBook Pro - Tech Specs - Apple

Search Precision Context Concurrent requests Minimum speed Architecture Type Maker Sort

Fit	Model	Parameters / active	Precision	Memory	Est. speed	Longest context	Runs as
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	IQ4_XS	42.4 / 48.0 GB	171–257 tok/s	256K	Unified memory
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	IQ4_XS	42.4 / 48.0 GB	171–257 tok/s	256K	Unified memory
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	IQ4_XS	41.6 / 48.0 GB	171–257 tok/s	256K	Unified memory
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 48.0 GB	91–137 tok/s	256K	Unified memory
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 48.0 GB	91–137 tok/s	256K	Unified memory
Runs well	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	Q4_K_M	21.9 / 48.0 GB	14–20 tok/s	112K	Unified memory
Runs well	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	Q4_K_Mmaker’s file	21.3 / 48.0 GB	14–21 tok/s	115K	Unified memory
Runs well	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	Q4_K_Mmaker’s file	21.3 / 48.0 GB	14–21 tok/s	115K	Unified memory
Runs well	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	Q4_K_Mmaker’s file	21.4 / 48.0 GB	14–21 tok/s	32K	Unified memory
Runs well	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	INT4 (AWQ / GPTQ)maker’s file	20.9 / 48.0 GB	14–21 tok/s	32K	Unified memory
Runs well	QwQ-32B Alibaba Qwen	32.8B	Q4_K_Mmaker’s file	21.4 / 48.0 GB	14–21 tok/s	40K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	Q4_K_M	21.5 / 48.0 GB	14–21 tok/s	32K	Unified memory
Runs well	Qwen3-32B Alibaba Qwen	32.8B	Q4_K_Mmaker’s file	21.3 / 48.0 GB	14–21 tok/s	128K	Unified memory
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	Q8_0	33.7 / 48.0 GB	55–82 tok/s	64K	Unified memory
Runs well	Gemma 4 31B IT Google	31.3B	Q5_K_M	23.8 / 48.0 GB	13–19 tok/s	163K	Unified memory
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	Q8_0	32.9 / 48.0 GB	52–78 tok/s	195K	Unified memory
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	Q8_0maker’s file	32.5 / 48.0 GB	63–94 tok/s	128K	Unified memory
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	Q8_0maker’s file	32.5 / 48.0 GB	63–94 tok/s	128K	Unified memory
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 48.0 GB	71–107 tok/s	256K	Unified memory
Runs well	Qwen3-30B-A3B-Thinking-2507 Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 48.0 GB	71–107 tok/s	256K	Unified memory
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	MLX 8bitmaker’s file	31.5 / 48.0 GB	73–109 tok/s	128K	Unified memory
Runs well	Qwen3-Coder-30B-A3B-Instruct Alibaba Qwen	30.5B / 3.3B	Q8_0	32.5 / 48.0 GB	71–107 tok/s	173K	Unified memory
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	Q8_0maker’s file	32.0 / 48.0 GB	77–115 tok/s	63K	Unified memory
Runs well	Granite Switch 4.1 30B IBM	30B	Q4_K_Mmaker’s file	22.6 / 48.0 GB	13–20 tok/s	106K	Unified memory
Runs well	Qwen3.5-27B Alibaba Qwen	27.8B	Q6_K	22.8 / 48.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Qwen3.6-27B Alibaba Qwen	27.8B	Q6_K	22.8 / 48.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Qwen3.8-27B Alibaba Qwen	27.8B	Q6_K	22.8 / 48.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	Q8_0	27.3 / 48.0 GB	67–100 tok/s	250K	Unified memory
Runs well	Magistral Small 1.2 Mistral AI	24B	Q6_K	20.5 / 48.0 GB	15–22 tok/s	125K	Unified memory
Runs well	Devstral Small 1.0 Mistral AI	23.6B	Q6_K	20.2 / 48.0 GB	15–22 tok/s	125K	Unified memory
Runs well	Devstral Small 1.1 Mistral AI	23.6B	Q6_K	20.2 / 48.0 GB	15–22 tok/s	125K	Unified memory
Runs well	Magistral Small 1.0 Mistral AI	23.6B	Q6_K	20.2 / 48.0 GB	15–22 tok/s	39K	Unified memory
Runs well	Magistral Small 1.1 Mistral AI	23.6B	Q6_K	20.2 / 48.0 GB	15–22 tok/s	39K	Unified memory
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	BF16 (native)maker’s file	43.1 / 48.0 GB	47–71 tok/s	97K	Unified memory
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 48.0 GB	119–179 tok/s	128K	Unified memory
Runs well	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	Q8_0	16.8 / 48.0 GB	18–27 tok/s	174K	Unified memory
Runs well	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	Q8_0maker’s file	16.9 / 48.0 GB	18–27 tok/s	32K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	Q8_0	16.8 / 48.0 GB	18–27 tok/s	32K	Unified memory
Runs well	Qwen3-14B Alibaba Qwen	14.8B	MLX 8bitmaker’s file	16.1 / 48.0 GB	19–28 tok/s	128K	Unified memory
Runs well	Gemma 3 12B IT Google	12.2B	Q8_0	15.5 / 48.0 GB	19–29 tok/s	100K	Unified memory
Runs well	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	BF16 (native)maker’s file	22.3 / 48.0 GB	13–20 tok/s	32K	Unified memory
Runs well	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 48.0 GB	15–22 tok/s	125K	Unified memory
Runs well	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 48.0 GB	16–24 tok/s	256K	Unified memory
Runs well	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 48.0 GB	16–25 tok/s	32K	Unified memory
Runs well	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 48.0 GB	16–24 tok/s	128K	Unified memory
Runs well	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 48.0 GB	16–25 tok/s	128K	Unified memory
Runs well	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 48.0 GB	16–25 tok/s	128K	Unified memory
Runs well	pplx-embed-v2-context-9b Perplexity	8.4B	Q8_0	9.1 / 48.0 GB	33–50 tok/s	256K	Unified memory
Runs well	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 48.0 GB	18–27 tok/s	125K	Unified memory
Runs well	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 48.0 GB	17–26 tok/s	128K	Unified memory
Runs well	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 48.0 GB	18–27 tok/s	125K	Unified memory
Runs well	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 48.0 GB	19–29 tok/s	125K	Unified memory
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 48.0 GB	109–163 tok/s	128K	Unified memory
Runs well	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 48.0 GB	20–29 tok/s	605K	Unified memory
Runs well	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 48.0 GB	20–29 tok/s	32K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 48.0 GB	20–29 tok/s	32K	Unified memory
Runs well	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 48.0 GB	20–30 tok/s	32K	Unified memory
Runs well	Gemma 4 E2B Google	5.1B	BF16 (native)maker’s file	10.1 / 48.0 GB	30–45 tok/s	125K	Unified memory
Runs well	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 48.0 GB	28–42 tok/s	256K	Unified memory
Runs well	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 48.0 GB	29–43 tok/s	31K	Unified memory
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	BF16 (native)maker’s file	9.4 / 48.0 GB	32–48 tok/s	256K	Unified memory
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	BF16 (native)maker’s file	9.9 / 48.0 GB	30–46 tok/s	250K	Unified memory
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 48.0 GB	33–50 tok/s	256K	Unified memory
Runs well	Qwen3-4B Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 48.0 GB	33–50 tok/s	128K	Unified memory
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 48.0 GB	110–165 tok/s	8K	Unified memory
Runs well	Granite-4.0-H-Micro IBM	3.2B	BF16 (native)maker’s file	6.5 / 48.0 GB	48–71 tok/s	128K	Unified memory
Runs well	Qwen3-1.7B Alibaba Qwen	2B	BF16 (native)maker’s file	5.2 / 48.0 GB	61–92 tok/s	40K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	BF16 (native)maker’s file	4.0 / 48.0 GB	81–122 tok/s	125K	Unified memory
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 48.0 GB	96–144 tok/s	128K	Unified memory
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 48.0 GB	126–189 tok/s	40K	Unified memory
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 48.0 GB	195–292 tok/s	256K	Unified memory
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 48.0 GB	144–216 tok/s	32K	Unified memory
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 48.0 GB	100–150 tok/s	8K	Unified memory
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 48.0 GB	100–150 tok/s	8K	Unified memory
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 48.0 GB	221–331 tok/s	512	Unified memory
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 48.0 GB	271–407 tok/s	514	Unified memory
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 48.0 GB	672–1008 tok/s	512	Unified memory
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 48.0 GB	2148–3222 tok/s	512	Unified memory
Runs, slowly	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	Q4_0	42.9 / 48.0 GB	7–10 tok/s	24K	Unified memory
Runs, slowly	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	Q4_0	42.9 / 48.0 GB	7–10 tok/s	24K	Unified memory
Runs, slowly	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	Q4_0maker’s file	43.0 / 48.0 GB	7–10 tok/s	24K	Unified memory
Runs, slowly	Qianfan-VL-70B Baidu	71.8B	Q4_0	42.0 / 48.0 GB	7–11 tok/s	27K	Unified memory
Runs, slowly	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	Q4_0	41.3 / 48.0 GB	7–11 tok/s	29K	Unified memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated