Qwen3-Coder-480B-A35B-Instruct — which GPUs fit

Alibaba · 480.2B (active 35B) · MoE · ctx 256K · apache-2.0 · HuggingFace

Qwen3-Coder-480B-A35B-Instruct (Alibaba) is a 480.2B parameters MoE (35B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 272.11 GB VRAM for Q4 (weights 264.11 GB + KV 7.0 GB + 1 GB overhead) and 968.4 GB for FP16. About 0 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 206.9 tok/s (estimated); MI300X 192GB ≈ 137.1 tok/s (estimated); H200 141GB SXM5 ≈ 67.0 tok/s (estimated). Use the table below for VRAM fit and tok/s per dollar (list MSRP). Estimates follow memory-bandwidth math; measured rows override when present. See methodology for details. Methodology.

10 hardware configs — sorted by tok/s. Default fit context 8K.

Hardware	VRAM	Quant	tok/s	Fits?	tok/s/$
B200 192GB SXM	192	Q4	206.9 est.	No	0.005
MI300X 192GB	192	Q4	137.1 est.	No	0.009
H200 141GB SXM5	141	Q4	67.0 est.	No	0.002
Gaudi 3 128GB	128	Q4	37.7 est.	No	0.003
Mac Studio M2 Ultra 192GB	192	Q4	20.7 est.	No	0.003
H100 80GB SXM5	80	Q4	15.0 est.	No	0.001
A100 80GB SXM4	80	Q4	9.2 est.	No	0.001
MacBook Pro M4 Max 128GB	128	Q4	6.3 est.	No	0.001
Mac Studio M3 Ultra 96GB	96	Q4	5.3 est.	No	0.001
MacBook Pro M3 Max 128GB	128	Q4	4.6 est.	No	0.001

Fit checks

Mac Studio M3 Ultra 96GB — does not fit · ≈5.3 tok/s Q4 est.
Mac Studio M2 Ultra 192GB — does not fit · ≈20.7 tok/s Q4 est.

12 popular retail GPUs; every row in the table above also links its Fits? verdict to the full fit check.

Same family: Qwen

Qwen3 Qwen3-8B · Qwen3-14B
Qwen3 2507 Qwen3-4B-Instruct-2507 · Qwen3-4B-Thinking-2507 · Qwen3-30B-A3B-Instruct-2507 · Qwen3-235B-A22B-Instruct-2507
Qwen2.5 Qwen2.5-7B-Instruct · Qwen2.5-14B-Instruct · Qwen2.5-32B-Instruct · Qwen2.5-72B-Instruct
Qwen2.5 Coder Qwen2.5-Coder-32B-Instruct
Qwen3 Next Qwen3-Next-80B-A3B-Instruct
Qwen3 Coder Qwen3-Coder-Next
Qwen3.5 Qwen3.5-2B · Qwen3.5-9B · Qwen3.5-27B · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-397B-A17B
Qwen3.6 Qwen3.6-27B · Qwen3.6-35B-A3B

All Qwen models →