Skip to content

Qwen3 VL 235B A22B Instruct on 2× RTX PRO 6000 Blackwell: VRAM, speed and fit

Qwen3 VL 235B A22B Instruct at 5-bit runs on the 2× RTX PRO 6000 Blackwell with 128K of context at about 55 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX PRO 6000 Blackwell · 5-bit (Q5_K_M) · Ollama / LM Studio · Chat

GPU memory
181 GB
of 192 GB
Context
128K
auto
Speed
55 tok/s
26 when full
First reply
0.7 s
2K prompt

Where the memory goes

Model
156 GB
Context
23.5 GB
Overhead
1.5 GB
OS
0.0 GB
Free
10.9 GB
Memory
181 GB of 192 GB
Context
128K tokens · auto
Speed
55 tok/s · 26 when full
First reply
0.7 s for a 2K prompt
Running cost
$18/mo at home · $287/mo on a cloud 4× A40

Validation: Validated

What Qwen3 VL 235B A22B Instruct on 2× RTX PRO 6000 Blackwell was checked against
CheckTargetResultStatus
Fits in GPU memory192 GB usable181 GB neededPass
Headroom5% free10.9 GB free (6%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more55 tok/sPass
First replyunder 3 s, 2K prompt0.7 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 VL 235B A22B Instruct
Parameters
236B, 22B active
Precision
5-bit (Q5_K_M)
Context
128K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX PRO 6000 Blackwell
GPU can use
192 GB of 192 GB

Running cost

At home
$18/mo
800 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct

Qwen3 VL 235B A22B Instruct on similar machines

Other models that run on 2× RTX PRO 6000 Blackwell

Questions

Can Qwen3 VL 235B A22B Instruct run on 2× RTX PRO 6000 Blackwell?

Qwen3 VL 235B A22B Instruct at 5-bit runs on the 2× RTX PRO 6000 Blackwell with 128K of context at about 55 tokens a second.

Report VR-1BJ4LPO, calculated Nov 22, 2026 from published specs, not benchmarked.