Skip to content

Qwen2.5 VL 32B Instruct on 2× RTX 5090: VRAM, speed and fit

Qwen2.5 VL 32B Instruct at 8-bit runs on the 2× RTX 5090 with 104K of context at about 34 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 5090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
60.7 GB
of 64.0 GB
Context
104K
auto
Speed
34 tok/s
19 when full
First reply
0.4 s
2K prompt

Where the memory goes

Model
33.1 GB
Context
26.0 GB
Overhead
1.6 GB
OS
0.0 GB
Free
3.3 GB
Memory
60.7 GB of 64.0 GB
Context
104K tokens · auto
Speed
34 tok/s · 19 when full
First reply
0.4 s for a 2K prompt
Running cost
$17/mo at home · $117/mo on a cloud 4× RTX 2000 Ada

Validation: Validated

What Qwen2.5 VL 32B Instruct on 2× RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory64.0 GB usable60.7 GB neededPass
Headroom5% free3.3 GB free (5%)Pass
Context for chat16K or more104KPass
Writing speed15 tok/s or more34 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
Qwen2.5 VL 32B Instruct
Parameters
33.5B
Precision
8-bit (Q8_0)
Context
104K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 5090
GPU can use
64.0 GB of 64.0 GB

Running cost

At home
$17/mo
770 W at the wall
Renting instead
$117/mo
4× RTX 2000 Ada at $0.96/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 bartowski/Qwen_Qwen2.5-VL-32B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-VL-32B-Instruct

Qwen2.5 VL 32B Instruct on similar machines

All machines: Qwen2.5 VL 32B Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 5090 run?

Other models that run on 2× RTX 5090

Questions

Can Qwen2.5 VL 32B Instruct run on 2× RTX 5090?

Qwen2.5 VL 32B Instruct at 8-bit runs on the 2× RTX 5090 with 104K of context at about 34 tokens a second.

Report VR-0S8N7OB, calculated Nov 22, 2026 from published specs, not benchmarked.