Phi 3.5 Mini Instruct on 2× RTX 3090: VRAM, speed and fit
Phi 3.5 Mini Instruct at 8-bit runs on the 2× RTX 3090 with 104K of context at about 143 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 2× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 43.9 GB
- of 48.0 GB
- Context
- 104K
- auto
- Speed
- 143 tok/s
- 14 when full
- First reply
- 0.1 s
- 2K prompt
Where the memory goes
- Model
- 3.8 GB
- Context
- 39.0 GB
- Overhead
- 1.1 GB
- OS
- 0.0 GB
- Free
- 4.1 GB
- Memory
- 43.9 GB of 48.0 GB
- Context
- 104K tokens · auto
- Speed
- 143 tok/s · 14 when full
- First reply
- 0.1 s for a 2K prompt
- Running cost
- $11/mo at home · $66/mo on a cloud 2× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 43.9 GB needed | Pass |
| Headroom | 5% free | 4.1 GB free (9%) | Pass |
| Context for chat | 16K or more | 104K | Pass |
| Writing speed | 15 tok/s or more | 143 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.1 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 3.5 Mini Instruct
- Parameters
- 3.8B
- Precision
- 8-bit (Q8_0)
- Context
- 104K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 2× RTX 3090
- GPU can use
- 48.0 GB of 48.0 GB
Running cost
- At home
- $11/mo
- 500 W at the wall
- Renting instead
- $66/mo
- 2× RTX A5000 at $0.54/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/Phi-3.5-mini-instruct-GGUF- vLLM
vllm serve microsoft/Phi-3.5-mini-instruct
Phi 3.5 Mini Instruct on similar machines
- RTX 3090Runs
- RTX 4090Runs
- Radeon AI PRO R9700Runs
- RTX 5090Runs
- 2× RTX 4090Runs
- RTX PRO 5000 Blackwell 48 GBRuns
- RTX 6000 AdaRuns
- L40SRuns
All machines: Phi 3.5 Mini Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?
Other models that run on 2× RTX 3090
Questions
Can Phi 3.5 Mini Instruct run on 2× RTX 3090?
Phi 3.5 Mini Instruct at 8-bit runs on the 2× RTX 3090 with 104K of context at about 143 tokens a second.
Report VR-05BDK43, calculated Nov 22, 2026 from published specs, not benchmarked.