What can a MacBook Pro M4 Pro 48GB run?

48GB · 273 GB/s · 60W · $2399

The serious laptop pick: 48 GB unified memory makes 30B-class MoE models genuinely usable on battery.

Runs great21

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	136 tok/s	33k
Qwen3-30B-A3B	Q6_K	62 tok/s	33k
Qwen3-Coder-30B-A3B	Q6_K	62 tok/s	58k
Gemma-3n-E4B	FP16	60 tok/s	131k
SmolLM2-1.7B	FP16	50 tok/s	8k
GPT-OSS-20B	Q8_0	44 tok/s	83k
Llama-3.2-3B	FP16	26 tok/s	131k
Phi-4-mini	FP16	22 tok/s	131k
Gemma-3-4B	FP16	22 tok/s	131k
Mistral-7B-Instruct	Q8_0	22 tok/s	33k
Qwen3-4B	FP16	22 tok/s	33k
DeepSeek-R1-Distill-Qwen-7B	Q8_0	21 tok/s	131k
Qwen2.5-Coder-7B	Q8_0	21 tok/s	131k
Llama-3.1-8B	Q8_0	20 tok/s	131k
Qwen3-8B	Q8_0	20 tok/s	33k
Qwen3-14B	Q4_K_M	17 tok/s	33k
Phi-4-14B	Q5_K_M	16 tok/s	16k
DeepSeek-R1-Distill-Qwen-14B	Q5_K_M	16 tok/s	131k
Gemma-3-12B	Q6_K	16 tok/s	131k

Tight squeeze11

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

Model	Quant	Est. speed	Max context
Codestral-22B	Q8_0	7 tok/s	33k
Llama-3.3-70B	IQ2_M	7 tok/s	57k
Qwen2.5-72B	IQ2_M	7 tok/s	53k
Mistral-Small-24B	Q8_0	7 tok/s	57k
Qwen3-32B	Q6_K	6 tok/s	33k
DeepSeek-R1-Distill-Qwen-32B	Q6_K	6 tok/s	46k
GLM-4-32B	Q6_K	6 tok/s	46k
Gemma-3-27B	Q8_0	6 tok/s	36k
Qwen3.8	Q8_0	6 tok/s	36k
Qwen3.8 27B	Q8_0	6 tok/s	36k
qwen35 27B	Q8_0	6 tok/s	34k

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