Skip to content

Qwen2.5 VL 3B Instruct on RTX 3080 10 GB: VRAM, speed and fit

Qwen2.5 VL 3B Instruct at 8-bit runs on the RTX 3080 10 GB with 125K of context at about 117 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3080 10 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
8.9 GB
of 10.0 GB
Context
125K
auto
Speed
117 tok/s
57 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
3.7 GB
Context
4.4 GB
Overhead
822 MB
OS
0.0 GB
Free
1.1 GB
Memory
8.9 GB of 10.0 GB
Context
125K tokens · auto
Speed
117 tok/s · 57 when full
First reply
0.3 s for a 2K prompt
Running cost
$5.95/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Qwen2.5 VL 3B Instruct on RTX 3080 10 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.0 GB usable8.9 GB neededPass
Headroom5% free1.1 GB free (11%)Pass
Context for chat16K or more125KPass
Writing speed15 tok/s or more117 tok/sPass
First replyunder 3 s, 2K prompt0.3 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 3B Instruct
Parameters
3.8B
Precision
8-bit (Q8_0)
Context
125K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 3080 10 GB
GPU can use
10.0 GB of 10.0 GB

Running cost

At home
$5.95/mo
272 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/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 ggml-org/Qwen2.5-VL-3B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-VL-3B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Nanonets-OCR2-3B-8bit

Qwen2.5 VL 3B Instruct on similar machines

All machines: Qwen2.5 VL 3B Instruct VRAM requirements. Everything that runs here: what can the RTX 3080 10 GB run?

Other models that run on RTX 3080 10 GB

Questions

Can Qwen2.5 VL 3B Instruct run on RTX 3080 10 GB?

Qwen2.5 VL 3B Instruct at 8-bit runs on the RTX 3080 10 GB with 125K of context at about 117 tokens a second.

Report VR-1SR8CGE, calculated Nov 22, 2026 from published specs, not benchmarked.