Can I run Qwen3-8B-MLX-4bit on an NVIDIA H200?

Yes

Its published weights (4.35 GB) fit in the 127 GB an NVIDIA H200 can use, with room for ≈ 40K tokens of context.

Full analysis of Qwen3-8B-MLX-4bit Everything that runs on NVIDIA H200 Get the weights on Hugging Face

hf download Qwen/Qwen3-8B-MLX-4bit

Files and context on NVIDIA H200

Each file of Qwen3-8B-MLX-4bit (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On NVIDIA H200	Context (16-bit)	Context (8-bit)
As published	4.35 GB	Fits	40K	40K

Qwen3-8B-MLX-4bit on other hardware

NVIDIA H200Yes
NVIDIA H100Yes
RTX 5090Yes
RTX 4090Yes
RTX 3090Yes
RTX 5060 Ti 16 GBYes
RTX 3060 12 GBYes
RTX 4060Yes
Mac with 32 GBYes
Mac with 64 GBYes
Mac with 128 GBYes

Popular models that run on NVIDIA H200

Qwen3-0.6BQwen · 752M
Qwen3-VL-8B-InstructQwen · 8.77B
gpt2openai-community · 137M
Qwen3-8BQwen · 8.19B
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
gemma-4-26B-A4B-itgoogle · 25.8B
Qwen2.5-7B-InstructQwen · 7.62B
Qwen3.5-9BQwen · 9.65B

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.