What can a MacBook Pro M4 Max 128GB run?

128GB · 546 GB/s · 100W · $4999

An unapologetic desktop in a laptop — 128 GB at 546 GB/s runs 70B Q4 at ~20 tok/s.

Runs great31

Comfortable headroom — daily-driver territory.

Model	Quant	Est. speed	Max context
deepseek moe 16b chat	FP16	Infinity tok/s	—
qwen2 7b instruct	FP16	Infinity tok/s	—
Qwen3-0.6B	FP16	273 tok/s	33k
Gemma-3n-E4B	FP16	121 tok/s	131k
GPT-OSS-120B	Q4_K_M	109 tok/s	103k
SmolLM2-1.7B	FP16	99 tok/s	8k
Llama-3.2-3B	FP16	53 tok/s	131k
Qwen3-30B-A3B	FP16	51 tok/s	33k
Qwen3-Coder-30B-A3B	FP16	51 tok/s	195k
GPT-OSS-20B	FP16	47 tok/s	131k
Phi-4-mini	FP16	44 tok/s	131k
Gemma-3-4B	FP16	44 tok/s	131k
Qwen3-4B	FP16	43 tok/s	33k
Gemma-3-12B	Q8_0	25 tok/s	131k
Mistral-7B-Instruct	FP16	23 tok/s	33k
DeepSeek-R1-Distill-Qwen-7B	FP16	22 tok/s	131k
Qwen2.5-Coder-7B	FP16	22 tok/s	131k
Phi-4-14B	Q8_0	22 tok/s	16k
DeepSeek-R1-Distill-Qwen-14B	Q8_0	22 tok/s	131k
Llama-3.1-8B	FP16	21 tok/s	131k
Qwen3-8B	FP16	21 tok/s	33k
Qwen3-14B	Q8_0	19 tok/s	33k
Codestral-22B	Q6_K	19 tok/s	33k
DeepSeek-R1-Distill-Qwen-32B	Q4_K_M	17 tok/s	131k
GLM-4-32B	Q4_K_M	17 tok/s	131k
Qwen3-32B	Q4_K_M	17 tok/s	33k
Mistral-Small-24B	Q6_K	17 tok/s	131k
Qwen3.8	Q6_K	15 tok/s	262k
Qwen3.8 27B	Q6_K	15 tok/s	262k
Gemma-3-27B	Q6_K	15 tok/s	131k
qwen35 27B	Q6_K	15 tok/s	452k

Tight squeeze5

It fits, but close the browser tabs and mind the context.

Model	Quant	Est. speed	Max context
Qwen3.8 Flash Next	Q3_K_M	231 tok/s	24k
Qwen3-235B-A22B	IQ2_M	46 tok/s	33k
Llama-3.3-70B	Q8_0	5 tok/s	89k
Qwen2.5-72B	Q8_0	4 tok/s	77k
glm-4.6-air 106B	Q6_K	4 tok/s	20k

Measured on this card0

Everything here was benchmarked on this exact card by someone who owns one — the tables above are our arithmetic; these numbers came off real machines.

Nobody has measured anything on this card yet. Paste a benchmark — it takes one keystroke and no form.

Try your own machine →← All hardware