Can I run Qwen3-32B-MLX-8bit on an RTX PRO 6000 Blackwell?

Yes

Its published weights (33.8 GB) fit in the 86.4 GB an RTX PRO 6000 Blackwell can use, with room for ≈ 40K tokens of context.

Full analysis of Qwen3-32B-MLX-8bit Everything that runs on RTX PRO 6000 Blackwell Get the weights on Hugging Face

hf download Qwen/Qwen3-32B-MLX-8bit

Files and context on RTX PRO 6000 Blackwell

Each file of Qwen3-32B-MLX-8bit (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 RTX PRO 6000 Blackwell	Context (16-bit)	Context (8-bit)
As published	33.8 GB	Fits	40K	40K
4-bit (estimate)	18.4 GB	Fits	40K	40K

Qwen3-32B-MLX-8bit on other hardware

NVIDIA H100Yes
RTX 5090Probably, at 4-bit
RTX 4090Probably, at 4-bit
RTX 3090Probably, at 4-bit
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
RTX PRO 6000 BlackwellYes
Mac with 32 GBProbably, at 4-bit
Mac with 64 GBYes
Mac with 128 GBYes

Popular models that run on RTX PRO 6000 Blackwell

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.