Best models for this Mac

27 modelsCatalog current through February 27, 2026

MacBook Pro M4 Max 48GB 16-inch ranked for coding with a most capable bias, using the best available runtime evidence.

Mac

Capability

Bias

Runtime

Use the strongest current runtime evidence for each row.M5 Max watch: 8B 61.6 tok/s · 14B 34.3 tok/s on the current 36GB public anchor.

Rank	Model	Score	Quant	Tok/s	Runtime	Evidence	Headroom	Why it ranks here
1	Qwen 3 32B	265	8bit	22.0 tok/s	Ollama	Estimated	15.0 GB	8bit is the highest practical quality here. 22.0 tok/s estimated from nearby benchmark coverage, with Ollama wrapper on llama.cpp as the best runtime hint. 15.0 GB headroom leaves workable context margin.
2	Devstral Small 1.1	261	8bit	43.0 tok/s	LM Studio	Estimated	23.9 GB	8bit is the highest practical quality here. 43.0 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 23.9 GB headroom leaves workable context margin.
3	Devstral Small 2 24B	261	8bit	25.3 tok/s	MLX	Estimated	23.9 GB	8bit is the highest practical quality here. 25.3 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 23.9 GB headroom leaves workable context margin.
4	Qwen3.5-27B	261	8bit	20.6 tok/s	MLX	Estimated	20.4 GB	8bit is the highest practical quality here. 20.6 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 20.4 GB headroom leaves workable context margin.
5	Gemma 3 27B	253	8bit	14.5 tok/s	LM Studio	Estimated	18.1 GB	8bit is the highest practical quality here. 14.5 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 18.1 GB headroom leaves workable context margin.
6	DeepSeek R1 Distill Qwen 32B	243	8bit	Measure it	Best available	Fit-first	15.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 15.0 GB headroom leaves workable context margin.
7	Mistral Small 3.1 24B	239	8bit	Measure it	Best available	Fit-first	23.9 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 23.9 GB headroom leaves workable context margin.
8	Magistral Small	239	8bit	Measure it	Best available	Fit-first	23.9 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 23.9 GB headroom leaves workable context margin.
9	Llama 3.3 70B	232	Q4_K_M	11.8 tok/s	LM Studio	Estimated	7.4 GB	Q4_K_M is the highest practical quality here. 11.8 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 7.4 GB headroom leaves workable context margin.
10	Nemotron-3-Nano-30B-A3B	228	8bit	43.7 tok/s	llama.cpp	Estimated	19.2 GB	8bit is the highest practical quality here. 43.7 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 19.2 GB headroom leaves workable context margin.
11	Qwen3-Coder-30B-A3B	227	8bit	58.5 tok/s	llama.cpp	Estimated	18.7 GB	8bit is the highest practical quality here. 58.5 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 18.7 GB headroom leaves workable context margin.
12	Qwen 3 30B-A3B	227	8bit	76.7 tok/s	MLX	Estimated	18.3 GB	8bit is the highest practical quality here. 76.7 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 18.3 GB headroom leaves workable context margin.
13	Qwen3.5-35B-A3B	222	8bit	80.0 tok/s	MLX	Estimated	14.3 GB	8bit is the highest practical quality here. 80.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 14.3 GB headroom leaves workable context margin.
14	GLM-4.7-Flash	220	8bit	36.8 tok/s	llama.cpp	Estimated	12.2 GB	8bit is the highest practical quality here. 36.8 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 12.2 GB headroom leaves workable context margin.
15	Qwen 3 8B	211	8bit	63.1 tok/s	LM Studio	Estimated	38.7 GB	8bit is the highest practical quality here. 63.1 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 38.7 GB headroom leaves workable context margin.
16	Llama 2 7B	209	8bit	36.4 tok/s	llama.cpp	Estimated	37.2 GB	8bit is the highest practical quality here. 36.4 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 37.2 GB headroom leaves workable context margin.
17	Qwen3.5-9B	206	8bit	15.0 tok/s	llama.cpp	Estimated	38.1 GB	8bit is the highest practical quality here. 15.0 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 38.1 GB headroom leaves workable context margin.
18	Qwen 2.5 14B	199	8bit	Measure it	Best available	Fit-first	33.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 33.0 GB headroom leaves workable context margin.
19	Phi-4 14B	198	8bit	Measure it	Best available	Fit-first	33.5 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 33.5 GB headroom leaves workable context margin.
20	Llama 3.1 8B	189	8bit	Measure it	Best available	Fit-first	39.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 39.0 GB headroom leaves workable context margin.
21	Qwen 2.5 7B	189	8bit	Measure it	Best available	Fit-first	40.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 40.0 GB headroom leaves workable context margin.
22	Mistral 7B v0.3	188	8bit	Measure it	Best available	Fit-first	39.7 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 39.7 GB headroom leaves workable context margin.
23	Gemma 3 4B	150	8bit	100.5 tok/s	LM Studio	Estimated	42.4 GB	8bit is the highest practical quality here. 100.5 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 42.4 GB headroom leaves workable context margin.
24	Qwen 3 4B	150	8bit	143.2 tok/s	MLX	Estimated	42.6 GB	8bit is the highest practical quality here. 143.2 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 42.6 GB headroom leaves workable context margin.
25	Qwen3-Coder-Next	149	q4.1bit	74.0 tok/s	MLX	Estimated	8.6 GB	q4.1bit is the highest practical quality here. 74.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 8.6 GB headroom leaves workable context margin.
26	Qwen 3 0.6B	145	8bit	184.4 tok/s	LM Studio	Estimated	46.8 GB	8bit is the highest practical quality here. 184.4 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 46.8 GB headroom leaves workable context margin.
27	Llama 3.2 1B	124	8bit	Measure it	Best available	Fit-first	46.1 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 46.1 GB headroom leaves workable context margin.

Machine

48GBUnified memory

$3,999MSRP

macbook_proForm factor

m4-maxChip