Skip to content

Qwen2.5 VL 32B Instruct on RTX 3090: VRAM, speed and fit

Qwen2.5 VL 32B Instruct at 3-bit runs on the RTX 3090 with 24K of context at about 38 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3090 · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
22.1 GB
of 24.0 GB
Context
24K
auto
Speed
38 tok/s
28 when full
First reply
2.0 s
2K prompt

Where the memory goes

Model
15.2 GB
Context
6.0 GB
Overhead
918 MB
OS
0.0 GB
Free
1.9 GB
Memory
22.1 GB of 24.0 GB
Context
24K tokens · auto
Speed
38 tok/s · 28 when full
First reply
2.0 s for a 2K prompt
Running cost
$6.35/mo at home · $33/mo on a cloud RTX A5000

Validation: Validated

What Qwen2.5 VL 32B Instruct on RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory24.0 GB usable22.1 GB neededPass
Headroom5% free1.9 GB free (8%)Pass
Context for chat16K or more24KPass
Writing speed15 tok/s or more38 tok/sPass
First replyunder 3 s, 2K prompt2.0 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
3-bit (Q3_K_M)
Context
24K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 3090
GPU can use
24.0 GB of 24.0 GB

Worth trying

  • 8-bit cache: Room for 48K context

Running cost

At home
$6.35/mo
290 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/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

  • RTX 4080 SuperJust misses
  • RTX 5070 TiJust misses
  • RTX 5080Just misses
  • Radeon RX 7900 XTXRuns
  • RTX 4090Runs
  • Radeon AI PRO R9700Runs
  • RTX 5090Runs
  • 2× RTX 3090Runs

All machines: Qwen2.5 VL 32B Instruct VRAM requirements. Everything that runs here: what can the RTX 3090 run?

Other models that run on RTX 3090

Questions

Can Qwen2.5 VL 32B Instruct run on RTX 3090?

Qwen2.5 VL 32B Instruct at 3-bit runs on the RTX 3090 with 24K of context at about 38 tokens a second.

Report VR-0ADP63O, calculated Nov 22, 2026 from published specs, not benchmarked.