Phi 2 on RTX 3080 10 GB: VRAM, speed and fit
Phi 2 at 8-bit runs on the RTX 3080 10 GB with 2K of context at about 160 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
- 4.0 GB
- of 10.0 GB
- Context
- 2K
- auto
- Speed
- 160 tok/s
- 133 when full
- First reply
- 0.2 s
- 2K prompt
Where the memory goes
- Model
- 2.8 GB
- Context
- 640 MB
- Overhead
- 641 MB
- OS
- 0.0 GB
- Free
- 6.0 GB
- Memory
- 4.0 GB of 10.0 GB
- Context
- 2K tokens · auto
- Speed
- 160 tok/s · 133 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
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 10.0 GB usable | 4.0 GB needed | Pass |
| Headroom | 5% free | 6.0 GB free (60%) | Pass |
| Context for chat | 2K or more | 2K | Pass |
| Writing speed | 15 tok/s or more | 160 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.2 s | Pass |
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
- Phi 2
- Parameters
- 2.8B
- Precision
- 8-bit (Q8_0)
- Context
- 2K, 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 TheBloke/phi-2-GGUF- vLLM
vllm serve microsoft/phi-2- Model card
- huggingface.co/microsoft/phi-2
Phi 2 on similar machines
- RTX 4060Runs
- RTX 5060Runs
- RTX 3070Runs
- RTX 3060 12 GBRuns
- Arc B580Runs
- RTX 4070Runs
- RTX 4070 SuperRuns
All machines: Phi 2 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 Phi 2 run on RTX 3080 10 GB?
Phi 2 at 8-bit runs on the RTX 3080 10 GB with 2K of context at about 160 tokens a second.
Report VR-199UV8C, calculated Nov 22, 2026 from published specs, not benchmarked.