Skip to content

InternVL2 5 4B MPO on RTX 3080 10 GB: VRAM, speed and fit

InternVL2 5 4B MPO at 8-bit runs on the RTX 3080 10 GB with 32K of context at about 127 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
5.6 GB
of 10.0 GB
Context
32K
auto
Speed
127 tok/s
99 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
3.7 GB
Context
1.1 GB
Overhead
821 MB
OS
0.0 GB
Free
4.4 GB
Memory
5.6 GB of 10.0 GB
Context
32K tokens · auto
Speed
127 tok/s · 99 when full
First reply
0.2 s for a 2K prompt
Running cost
$5.95/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What InternVL2 5 4B MPO on RTX 3080 10 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.0 GB usable5.6 GB neededPass
Headroom5% free4.4 GB free (44%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more127 tok/sPass
First replyunder 3 s, 2K prompt0.2 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
InternVL2 5 4B MPO
Parameters
3.7B
Precision
8-bit (Q8_0)
Context
32K, 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 22, 2026.

How to run it

llama.cpp
llama-server -hf mradermacher/InternVL2_5-4B-MPO-GGUF
vLLM
vllm serve OpenGVLab/InternVL2_5-4B-MPO

InternVL2 5 4B MPO on similar machines

All machines: InternVL2 5 4B MPO 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 InternVL2 5 4B MPO run on RTX 3080 10 GB?

InternVL2 5 4B MPO at 8-bit runs on the RTX 3080 10 GB with 32K of context at about 127 tokens a second.

Report VR-17IJ77A, calculated Nov 22, 2026 from published specs, not benchmarked.