How many AI models can I run with 128 GB VRAM?

With 128 GB VRAM, you can comfortably run 97 AI models at recommended quantization levels. An additional 2 models fit with tight memory margins.

What is the largest model I can run with 128 GB VRAM?

The largest model you can run with 128 GB VRAM is Mixtral 8x22B (141B parameters) at Q4_K_M quantization, requiring 86 GB.

What GPUs have 128 GB VRAM?

There are few discrete GPUs at exactly 128 GB. Check nearby VRAM tiers for available options.

Best AI Models for 128 GB VRAM

Maximum consumer — 200B+ models, research workloads. Here are all 99 models you can run locally with 128 GB of memory.

Hardware with 128 GB Memory

Mac Studio M4 Max 128GB MacBook Pro M4 Max 128GB MacBook Pro M5 Max 128GB

Runs Comfortably (97)

These models fit with room to spare for context window and OS overhead.

Model	Params	Quantization	VRAM	Quality
Mixtral 8x22B	141B	Q4_K_M	86 GB	4
Devstral 2 123B	123B	Q4_K_M	67 GB	4
Mistral Large 2 123B	123B	Q4_K_M	67 GB	4
Qwen 3.5 122B	122B	Q4_K_M	85 GB	4
gpt-oss 120B	117B	MXFP4	70 GB	4
Llama 4 Scout (109B/17B active)	109B	Q4_K_M	72 GB	4
Llama 3.2 Vision 90B	90B	Q8_0	96 GB	4
Qwen 2.5 72B	72B	Q8_0	74 GB	5
Qwen 2.5 VL 72B	72B	Q8_0	78 GB	4
Cogito 70B	70B	Q8_0	76 GB	4
DeepSeek R1 70B	70B	Q8_0	72 GB	5
Llama 3.1 70B	70B	Q8_0	72 GB	5
Llama 3.3 70B	70B	Q8_0	72 GB	5
Dolphin Mixtral 8x7B	47B	F16	94 GB	5
Mixtral 8x7B	47B	Q8_0	49 GB	5
Command R 35B	35B	Q8_0	37 GB	5
Qwen 3.5 35B A3B	35B	Q8_0	20 GB	5
Qwen 3.6 35B-A3B	35B	BF16	78 GB	5
Nous Hermes 2 34B	34B	F16	70 GB	5
Yi 1.5 34B	34B	F16	70 GB	5
Laguna XS 2.1	33B	BF16	72 GB	5
WizardCoder 33B	33B	F16	69.5 GB	5
Aya Expanse 32B	32B	Q8_0	38 GB	5
Cogito 32B	32B	F16	68 GB	5
DeepSeek R1 32B	32B	Q8_0	34 GB	5
Qwen 2.5 32B	32B	Q8_0	34 GB	5
Qwen 2.5 Coder 32B	32B	F16	70 GB	5
Qwen 3 32B	32B	F16	70 GB	5
QwQ 32B	32B	F16	68 GB	5
Gemma 4 31B	31B	F16	66 GB	5
Qwen 3 30B-A3B (MoE)	30B	F16	67 GB	5
Gemma 2 27B	27B	Q8_0	29 GB	5
Gemma 3 27B	27B	F16	60 GB	5
Qwen 3.5 27B	27B	Q8_0	33 GB	5
Qwen 3.6 27B	27B	BF16	62 GB	5
Gemma 4 26B	26B	Q8_0	30 GB	5
Devstral 24B	24B	F16	53 GB	5
Magistral Small 24B	24B	F16	52 GB	5
Mistral Small 3.1 24B	24B	F16	54 GB	5
Codestral 22B	22B	Q8_0	24 GB	5
gpt-oss 20B	21B	MXFP4	15 GB	4
InternLM 2.5 20B	20B	F16	42 GB	5
StarCoder2 15B	15B	Q8_0	17 GB	5
DeepSeek R1 14B	14B	Q8_0	16 GB	5
Phi-4 14B	14B	Q8_0	16 GB	5
Phi-4 Reasoning 14B	14B	F16	32 GB	5
Qwen 2.5 14B	14B	Q8_0	16 GB	5
Qwen 2.5 Coder 14B	14B	F16	33 GB	5
Qwen 3 14B	14B	F16	33 GB	5
Gemma 3 12B	12B	F16	28 GB	5
Mistral Nemo 12B	12B	F16	28 GB	5
Llama 3.2 Vision 11B	11B	F16	26 GB	5
Falcon 3 10B	10B	F16	24 GB	5
Gemma 2 9B	9B	F16	20 GB	5
Qwen 3.5 9B	9B	Q8_0	11.5 GB	5
Yi 1.5 9B	9B	F16	20 GB	5
Yi Coder 9B	9B	F16	21 GB	5
Aya Expanse 8B	8B	Q8_0	10.5 GB	5
Cogito 8B	8B	F16	19.5 GB	5
DeepSeek R1 8B	8B	F16	20 GB	5
Dolphin 3 8B	8B	F16	18 GB	5
Granite 3.3 8B	8B	F16	18 GB	5
Llama 3.1 8B	8B	F16	18 GB	5
Nemotron 3 Nano 8B	8B	F16	19.5 GB	5
Nous Hermes 2 8B	8B	F16	18 GB	5
Qwen 3 8B	8B	F16	20 GB	5
Codestral Mamba 7B	7B	F16	17 GB	5
DeepSeek R1 7B	7B	F16	16 GB	5
Falcon 3 7B	7B	F16	17.5 GB	5
InternLM 2.5 7B	7B	F16	16 GB	5
Mistral 7B	7B	F16	16 GB	5
OpenChat 3.5 7B	7B	F16	17 GB	5
Qwen 2.5 7B	7B	F16	16 GB	5
Qwen 2.5 Coder 7B	7B	F16	16 GB	5
Qwen 2.5 VL 7B	7B	F16	18.5 GB	5
StarCoder2 7B	7B	F16	16 GB	5
WizardLM 2 7B	7B	F16	17 GB	5
Yi 1.5 6B	6B	F16	14 GB	5
Gemma 3 4B	4B	F16	11.5 GB	5
Gemma 3n E4B	4B	F16	11 GB	5
Gemma 4 E4B	4B	Q8_0	10 GB	5
Qwen 3 4B	4B	F16	11 GB	5
Qwen 3.5 4B	4B	Q8_0	6.5 GB	4
Phi-3 Mini 3.8B	3.8B	F16	9.6 GB	5
Phi-4 Mini 3.8B	3.8B	F16	10.5 GB	5
Llama 3.2 3B	3B	F16	8 GB	5
StarCoder2 3B	3B	F16	8 GB	5
Gemma 2 2B	2B	F16	6 GB	5
Gemma 3n E2B	2B	F16	6.5 GB	5
Gemma 4 E2B	2B	Q8_0	6 GB	5
Qwen 3.5 2B	2B	Q8_0	4.5 GB	4
SmolLM2 1.7B	1.7B	F16	4.4 GB	5
DeepSeek R1 1.5B	1.5B	F16	5 GB	5
Gemma 3 1B	1B	F16	3.5 GB	5
Llama 3.2 1B	1B	F16	4 GB	5
Qwen 3.5 0.8B	0.8B	Q8_0	2 GB	4
Qwen 3 0.6B	0.6B	F16	3.3 GB	5

Tight Fit (2)

These models run but with limited context window. Close other apps to free memory.

Model	Params	Quantization	VRAM	Quality
Command A 111B	111B	Q8_0	117 GB	5
Command R+ 104B	104B	Q8_0	110 GB	5

Want to check a specific combination?

Use the compatibility checker to see exactly how a model runs on your specific hardware, with performance estimates.

Open Compatibility Checker

8 GBEntry-level local AI 12 GBThe minimum for a good experience 16 GBThe sweet spot 24 GBSerious local AI