Skip to content

MiniCPM V 4.6 on RTX 3080 10 GB: VRAM, speed and fit

MiniCPM V 4.6 at 8-bit runs on the RTX 3080 10 GB with 256K of context at about 298 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
5.3 GB
of 10.0 GB
Context
256K
auto
Speed
298 tok/s
106 when full
First reply
0.1 s
2K prompt

Where the memory goes

Model
1.3 GB
Context
3.0 GB
Overhead
1.0 GB
OS
0.0 GB
Free
4.7 GB
Memory
5.3 GB of 10.0 GB
Context
256K tokens · auto
Speed
298 tok/s · 106 when full
First reply
0.1 s for a 2K prompt
Running cost
$5.95/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What MiniCPM V 4.6 on RTX 3080 10 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.0 GB usable5.3 GB neededPass
Headroom5% free4.7 GB free (47%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more298 tok/sPass
First replyunder 3 s, 2K prompt0.1 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
MiniCPM V 4.6
Parameters
1.3B
Precision
8-bit (Q8_0)
Context
256K, 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 openbmb/MiniCPM-OCR-1.0-gguf
vLLM
vllm serve openbmb/MiniCPM-V-4.6
MLX (Mac)
mlx_lm.chat --model mlx-community/MiniCPM-V-4.6-4bit

MiniCPM V 4.6 on similar machines

  • RTX 4060Runs
  • RTX 5060Runs
  • RTX 3070Runs
  • RTX 3060 12 GBRuns
  • Arc B580Runs
  • RTX 4070Runs
  • RTX 4070 SuperRuns

All machines: MiniCPM V 4.6 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 MiniCPM V 4.6 run on RTX 3080 10 GB?

MiniCPM V 4.6 at 8-bit runs on the RTX 3080 10 GB with 256K of context at about 298 tokens a second.

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