4× RTX PRO 6000
235tok/sEveryday
1 request, prose prompt, context 19, with DSpark (per recipe) Source
Intelligence34with thinking
- Custom kernel required
Local AI · Recipe · 8× RTX PRO 6000
DeepSeek-V4-Flash 284B-A13B FP8 with vLLM on 8× RTX PRO 6000
DeepSeek-V4-Flash 284B-A13B FP8 with vLLM on 8× RTX PRO 6000: 245 tok/s according to github.com (dataset as of Nov 3, 2026).
by helixml
Engine
- Engine
- vLLM vLLM + SparkInfer (Fork)
- Quantization
- FP8 (~156 GB)
- Model family
- DeepSeek-V4-Flash
- Context
- —
- Parameters
- 284B MoE / 13B active
- Creator
- helixml
- GitHub stars
- 9
- Repo updated
- Oct 26, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
What you need
- Hardware
- 8 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsdeepseek-ai/DeepSeek-V4-Flash-0731 MIT
- Engine
- vLLM vLLM + SparkInfer (Fork)
Related recipes
4× DGX Spark
46tok/sEveryday
1 request, prose prompt, with DSpark Source
Intelligenceno independent value
4× DGX Spark
42tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- Custom kernel required
3× DGX Spark
41.9tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- Custom kernel required
2× DGX Spark
33.2tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
30.2tok/sEveryday
1 request, story prompt, prompt 18 tokens, with MTP (per recipe) Source
Intelligence34with thinking
- ≤ 3 bit: quantization may cost quality
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.