DeepSeek V4.1 Flash on 8× RTX PRO 6000 Blackwell: VRAM, speed and fit
DeepSeek V4.1 Flash at FP4 + FP8 runs on the 8× RTX PRO 6000 Blackwell with 1M of context at about 63 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 8× RTX PRO 6000 Blackwell · FP4 + FP8 · Ollama / LM Studio · Chat
- GPU memory
- 483 GB
- of 768 GB
- Context
- 1M
- auto
- Speed
- 63 tok/s
- Very fast
- First reply
- 0.3 s
- 2K prompt
Where the memory goes
- Model
- 475 GB
- Context
- 2.6 GB
- Overhead
- 5.4 GB
- OS
- 0.0 GB
- Free
- 285 GB
- Memory
- 483 GB of 768 GB
- Context
- 1M tokens · auto
- Speed
- 63 tok/s · very fast
- First reply
- 0.3 s for a 2K prompt
- Running cost
- $65/mo at home · $1,162/mo on a cloud 4× MI300X
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 768 GB usable | 483 GB needed | Pass |
| Headroom | 5% free | 285 GB free (37%) | Pass |
| Context for chat | 16K or more | 1M | Pass |
| Writing speed | 15 tok/s or more | 63 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.3 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
- DeepSeek V4.1 Flash
- Parameters
- 763B, 16B active
- Precision
- FP4 + FP8
- Context
- 1M, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 8× RTX PRO 6000 Blackwell
- GPU can use
- 768 GB of 768 GB
Running cost
- At home
- $65/mo
- 2960 W at the wall
- Renting instead
- $1,162/mo
- 4× MI300X at $9.56/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 unsloth/DeepSeek-V4.1-Flash-1017-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V4.1-Flash- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4.1-Flash-MLX-4bit
DeepSeek V4.1 Flash on similar machines
- Dual DGX SparkRuns
- DGX Station GB300Runs
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
- H100 SXMToo big
- 4× H200 NVLRuns
- 8× H200 NVLRuns
All machines: DeepSeek V4.1 Flash VRAM requirements. Everything that runs here: what can the 8× RTX PRO 6000 Blackwell run?
Other models that run on 8× RTX PRO 6000 Blackwell
Questions
Can DeepSeek V4.1 Flash run on 8× RTX PRO 6000 Blackwell?
DeepSeek V4.1 Flash at FP4 + FP8 runs on the 8× RTX PRO 6000 Blackwell with 1M of context at about 63 tokens a second.
Report VR-1AKKLIF, calculated Nov 22, 2026 from published specs, not benchmarked.