Step 3.5 Flash on 4× RTX 3090: VRAM, speed and fit
Step 3.5 Flash at 2-bit runs on the 4× RTX 3090 with 48K of context at about 124 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× RTX 3090 · 2-bit (Q2_K) · Ollama / LM Studio · Chat
- GPU memory
- 90.9 GB
- of 96.0 GB
- Context
- 48K
- auto
- Speed
- 124 tok/s
- 26 when full
- First reply
- 0.5 s
- 2K prompt
Where the memory goes
- Model
- 69.6 GB
- Context
- 18.6 GB
- Overhead
- 2.7 GB
- OS
- 0.0 GB
- Free
- 5.1 GB
- Memory
- 90.9 GB of 96.0 GB
- Context
- 48K tokens · auto
- Speed
- 124 tok/s · 26 when full
- First reply
- 0.5 s for a 2K prompt
- Running cost
- $20/mo at home · $131/mo on a cloud 4× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 96.0 GB usable | 90.9 GB needed | Pass |
| Headroom | 5% free | 5.1 GB free (5%) | Pass |
| Context for chat | 16K or more | 48K | Pass |
| Writing speed | 15 tok/s or more | 124 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.5 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
- Step 3.5 Flash
- Parameters
- 199B, 9.4B active
- Precision
- 2-bit (Q2_K)
- Context
- 48K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 4× RTX 3090
- GPU can use
- 96.0 GB of 96.0 GB
Worth trying
- 8-bit cache: Room for 88K context
Running cost
- At home
- $20/mo
- 920 W at the wall
- Renting instead
- $131/mo
- 4× RTX A5000 at $1.08/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 ggml-org/Step-3.5-Flash-GGUF- vLLM
vllm serve stepfun-ai/Step-3.5-Flash- MLX (Mac)
mlx_lm.chat --model mlx-community/Step-3.5-Flash-4bit- Model card
- huggingface.co/stepfun-ai/Step-3.5-Flash
Step 3.5 Flash on similar machines
- RTX PRO 5000 Blackwell 48 GBToo big
- RTX 6000 AdaToo big
- L40SToo big
- 2× RTX 5090Just misses
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 32 GBToo big
All machines: Step 3.5 Flash VRAM requirements. Everything that runs here: what can the 4× RTX 3090 run?
Other models that run on 4× RTX 3090
Questions
Can Step 3.5 Flash run on 4× RTX 3090?
Step 3.5 Flash at 2-bit runs on the 4× RTX 3090 with 48K of context at about 124 tokens a second.
Report VR-12AYR0K, calculated Nov 22, 2026 from published specs, not benchmarked.