MacBook Pro M5 Max 128GB

Apple · M5 Max · 128GB Unified Memory · Can run 102 models

Manufacturer	Apple
Unified Mem	128 GB
Chip	M5 Max
CPU Cores	16
GPU Cores	40
Neural Engine	16
Bandwidth	546 GB/s
MSRP	$4,999
Released	Mar 11, 2026

AI Notes

The MacBook Pro M5 Max 128GB is the ultimate laptop for local AI inference. With 128GB of unified memory and 546 GB/s bandwidth, it can run the largest open-weight models including full 70B models at high quantization and even 100B+ models. The 40 GPU cores ensure fast token generation across all model sizes.

Compatible Models

Model	Parameters	Best Quant	VRAM Used	Fit	Est. Speed
Qwen 3 0.6B	600M	Q4_K_M	2.5 GB	Runs	~218 tok/s
Qwen 3.5 0.8B	800M	Q4_K_M	1.5 GB	Runs	~364 tok/s
Gemma 3 1B	1B	Q8_0	2 GB	Runs	~273 tok/s
Llama 3.2 1B	1B	Q8_0	3 GB	Runs	~182 tok/s
DeepSeek R1 1.5B	1.5B	Q8_0	3 GB	Runs	~182 tok/s
SmolLM2 1.7B	1.7B	Q8_0	2.7 GB	Runs	~202 tok/s
Gemma 2 2B	2B	Q8_0	4 GB	Runs	~137 tok/s
Gemma 3n E2B	2B	Q4_K_M	3.3 GB	Runs	~165 tok/s
Gemma 4 E2B	2B	Q4_K_M	4 GB	Runs	~137 tok/s
Qwen 3.5 2B	2B	Q4_K_M	3 GB	Runs	~182 tok/s
Llama 3.2 3B	3B	Q8_0	5 GB	Runs	~109 tok/s
StarCoder2 3B	3B	Q4_K_M	3.5 GB	Runs	~156 tok/s
Phi-3 Mini 3.8B	3.8B	Q8_0	5.8 GB	Runs	~94 tok/s
Phi-4 Mini 3.8B	3.8B	Q4_K_M	4.5 GB	Runs	~121 tok/s
Gemma 3 4B	4B	Q4_K_M	5 GB	Runs	~109 tok/s
Gemma 3n E4B	4B	Q4_K_M	4.5 GB	Runs	~121 tok/s
Gemma 4 E4B	4B	Q4_K_M	6 GB	Runs	~91 tok/s
Qwen 3 4B	4B	Q4_K_M	4.5 GB	Runs	~121 tok/s
Qwen 3.5 4B	4B	Q4_K_M	4.5 GB	Runs	~121 tok/s
Yi 1.5 6B	6B	Q4_K_M	5 GB	Runs	~109 tok/s
Codestral Mamba 7B	7B	Q4_K_M	6.9 GB	Runs	~79 tok/s
DeepSeek R1 7B	7B	Q8_0	9 GB	Runs	~61 tok/s
Falcon 3 7B	7B	Q4_K_M	6.8 GB	Runs	~80 tok/s
InternLM 2.5 7B	7B	Q4_K_M	5.5 GB	Runs	~99 tok/s
Mistral 7B	7B	Q8_0	9 GB	Runs	~61 tok/s
OpenChat 3.5 7B	7B	Q4_K_M	6.9 GB	Runs	~79 tok/s
Qwen 2.5 7B	7B	Q8_0	9 GB	Runs	~61 tok/s
Qwen 2.5 Coder 7B	7B	Q8_0	9 GB	Runs	~61 tok/s
Qwen 2.5 VL 7B	7B	Q4_K_M	7 GB	Runs	~78 tok/s
StarCoder2 7B	7B	Q4_K_M	5.5 GB	Runs	~99 tok/s
WizardLM 2 7B	7B	Q4_K_M	6.9 GB	Runs	~79 tok/s
Aya Expanse 8B	8B	Q4_K_M	6.5 GB	Runs	~84 tok/s
Cogito 8B	8B	Q4_K_M	7.5 GB	Runs	~73 tok/s
DeepSeek R1 8B	8B	Q4_K_M	7.5 GB	Runs	~73 tok/s
Dolphin 3 8B	8B	Q4_K_M	6 GB	Runs	~91 tok/s
Granite 3.3 8B	8B	Q8_0	10 GB	Runs	~55 tok/s
Llama 3.1 8B	8B	Q8_0	10 GB	Runs	~55 tok/s
Nemotron 3 Nano 8B	8B	Q4_K_M	7.5 GB	Runs	~73 tok/s
Nous Hermes 2 8B	8B	Q4_K_M	6 GB	Runs	~91 tok/s
Qwen 3 8B	8B	Q4_K_M	7.5 GB	Runs	~73 tok/s
Gemma 2 9B	9B	Q8_0	11 GB	Runs	~50 tok/s
Qwen 3.5 9B	9B	Q4_K_M	7.5 GB	Runs	~73 tok/s
Yi 1.5 9B	9B	Q4_K_M	6.5 GB	Runs	~84 tok/s
Yi Coder 9B	9B	Q4_K_M	8 GB	Runs	~68 tok/s
Falcon 3 10B	10B	Q4_K_M	8.5 GB	Runs	~64 tok/s
Llama 3.2 Vision 11B	11B	Q4_K_M	8.5 GB	Runs	~64 tok/s
Gemma 3 12B	12B	Q4_K_M	10.5 GB	Runs	~52 tok/s
Mistral Nemo 12B	12B	Q4_K_M	9.5 GB	Runs	~57 tok/s
DeepSeek R1 14B	14B	Q4_K_M	9.9 GB	Runs	~55 tok/s
Phi-4 14B	14B	Q4_K_M	9.9 GB	Runs	~55 tok/s
Phi-4 Reasoning 14B	14B	Q4_K_M	11 GB	Runs	~50 tok/s
Qwen 2.5 14B	14B	Q4_K_M	9.9 GB	Runs	~55 tok/s
Qwen 2.5 Coder 14B	14B	Q4_K_M	12 GB	Runs	~46 tok/s
Qwen 3 14B	14B	Q4_K_M	12 GB	Runs	~46 tok/s
StarCoder2 15B	15B	Q8_0	17 GB	Runs	~32 tok/s
InternLM 2.5 20B	20B	Q4_K_M	12 GB	Runs	~46 tok/s
gpt-oss 20B	21B	MXFP4	15 GB	Runs	~36 tok/s
Codestral 22B	22B	Q4_K_M	14.7 GB	Runs	~37 tok/s
Devstral 24B	24B	Q4_K_M	17 GB	Runs	~32 tok/s
Magistral Small 24B	24B	Q4_K_M	17 GB	Runs	~32 tok/s
Mistral Small 3.1 24B	24B	Q4_K_M	18 GB	Runs	~30 tok/s
Gemma 4 26B	26B	Q4_K_M	20 GB	Runs	~27 tok/s
Gemma 2 27B	27B	Q4_K_M	17.7 GB	Runs	~31 tok/s
Gemma 3 27B	27B	Q4_K_M	20 GB	Runs	~27 tok/s
Qwen 3.5 27B	27B	Q4_K_M	19 GB	Runs	~29 tok/s
Qwen 3.6 27B	27B	Q4_K_M	20 GB	Runs	~27 tok/s
Qwen 3 30B-A3B (MoE)	30B	Q4_K_M	22 GB	Runs	~25 tok/s
Gemma 4 31B	31B	Q4_K_M	22 GB	Runs	~25 tok/s
Aya Expanse 32B	32B	Q4_K_M	22 GB	Runs	~25 tok/s
Cogito 32B	32B	Q4_K_M	21.5 GB	Runs	~25 tok/s
DeepSeek R1 32B	32B	Q4_K_M	20.7 GB	Runs	~26 tok/s
Qwen 2.5 32B	32B	Q4_K_M	20.7 GB	Runs	~26 tok/s
Qwen 2.5 Coder 32B	32B	Q4_K_M	23 GB	Runs	~24 tok/s
Qwen 3 32B	32B	Q4_K_M	23 GB	Runs	~24 tok/s
QwQ 32B	32B	Q4_K_M	21.5 GB	Runs	~25 tok/s
Laguna XS 2.1	33B	Q4_K_M	22 GB	Runs	~25 tok/s
WizardCoder 33B	33B	Q4_K_M	22 GB	Runs	~25 tok/s
Nous Hermes 2 34B	34B	Q4_K_M	19 GB	Runs	~29 tok/s
Yi 1.5 34B	34B	Q4_K_M	21 GB	Runs	~26 tok/s
Command R 35B	35B	Q4_K_M	22.5 GB	Runs	~24 tok/s
Qwen 3.5 35B A3B	35B	Q4_K_M	12 GB	Runs	~46 tok/s
Qwen 3.6 35B-A3B	35B	Q4_K_M	27 GB	Runs	~20 tok/s
Dolphin Mixtral 8x7B	47B	Q4_K_M	26 GB	Runs	~21 tok/s
Mixtral 8x7B	47B	Q4_K_M	29.7 GB	Runs	~18 tok/s
Cogito 70B	70B	Q4_K_M	43 GB	Runs	~13 tok/s
DeepSeek R1 70B	70B	Q4_K_M	43.5 GB	Runs	~13 tok/s
Llama 3.1 70B	70B	Q4_K_M	43.5 GB	Runs	~13 tok/s
Llama 3.3 70B	70B	Q4_K_M	43.5 GB	Runs	~13 tok/s
Qwen 2.5 72B	72B	Q4_K_M	44.7 GB	Runs	~12 tok/s
Qwen 2.5 VL 72B	72B	Q4_K_M	41 GB	Runs	~13 tok/s
Llama 3.2 Vision 90B	90B	Q4_K_M	50 GB	Runs	~11 tok/s
Command R+ 104B	104B	Q4_K_M	57 GB	Runs	~10 tok/s
Llama 4 Scout (109B/17B active)	109B	Q4_K_M	72 GB	Runs	~8 tok/s
Command A 111B	111B	Q4_K_M	61 GB	Runs	~9 tok/s
gpt-oss 120B	117B	MXFP4	70 GB	Runs	~8 tok/s
Qwen 3.5 122B	122B	Q4_K_M	85 GB	Runs	~6 tok/s
Devstral 2 123B	123B	Q4_K_M	67 GB	Runs	~8 tok/s
Mistral Large 2 123B	123B	Q4_K_M	67 GB	Runs	~8 tok/s
Mixtral 8x22B	141B	Q4_K_M	86 GB	Runs	~6 tok/s
Qwen 3 235B-A22B	235B	Q4_K_M	138 GB	CPU Offload	~1 tok/s
Nemotron Ultra 253B	253B	Q4_K_M	155 GB	CPU Offload	~1 tok/s
MiniMax M3	428B	Q2_K	163 GB	CPU Offload	~1 tok/s

12 model(s) are too large for this hardware.