Skip to content

Qwen3 235B A22B on 4× H200 NVL: VRAM, speed and fit

Qwen3 235B A22B at 8-bit runs on the 4× H200 NVL with 40K of context at about 79 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× H200 NVL · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
243 GB
of 564 GB
Context
40K
auto
Speed
79 tok/s
67 when full
First reply
0.4 s
2K prompt

Where the memory goes

Model
233 GB
Context
7.3 GB
Overhead
2.8 GB
OS
0.0 GB
Free
321 GB
Memory
243 GB of 564 GB
Context
40K tokens · auto
Speed
79 tok/s · 67 when full
First reply
0.4 s for a 2K prompt
Running cost
$33/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What Qwen3 235B A22B on 4× H200 NVL was checked against
CheckTargetResultStatus
Fits in GPU memory564 GB usable243 GB neededPass
Headroom5% free321 GB free (57%)Pass
Context for chat16K or more40KPass
Writing speed15 tok/s or more79 tok/sPass
First replyunder 3 s, 2K prompt0.4 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Qwen3 235B A22B
Parameters
235B, 22B active
Precision
8-bit (Q8_0)
Context
40K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× H200 NVL
GPU can use
564 GB of 564 GB

Running cost

At home
$33/mo
1520 W at the wall
Renting instead
$574/mo
8× A40 at $4.72/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/Qwen3-235B-A22B-GGUF
vLLM
vllm serve Qwen/Qwen3-235B-A22B
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-235B-A22B-4bit

Qwen3 235B A22B on similar machines

All machines: Qwen3 235B A22B VRAM requirements. Everything that runs here: what can the 4× H200 NVL run?

Other models that run on 4× H200 NVL

Questions

Can Qwen3 235B A22B run on 4× H200 NVL?

Qwen3 235B A22B at 8-bit runs on the 4× H200 NVL with 40K of context at about 79 tokens a second.

Report VR-02QYVTR, calculated Nov 22, 2026 from published specs, not benchmarked.