MacBook Pro M4 Max 128GB

Apple · M4 Max · 128GB Unified Memory · Can run 102 models

Manufacturer	Apple
Unified Mem	128 GB
Chip	M4 Max
CPU Cores	16
GPU Cores	40
Neural Engine	16
Bandwidth	546 GB/s
MSRP	$4,999
Released	Nov 8, 2024

AI Notes

The MacBook Pro M4 Max 128GB is the ultimate laptop for local AI. With 128GB of unified memory, it can run 70B models at full precision and even load larger models like Llama 3.1 405B with heavy quantization. The 546 GB/s memory bandwidth ensures excellent inference throughput for the most demanding AI workloads on the go.

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.