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 · 1× RTX PRO 6000
DeepSeek-V4-Flash 284B MXFP4 with vLLM on 1× RTX PRO 6000 (300k context)
DeepSeek-V4-Flash 284B MXFP4 with vLLM on 1× RTX PRO 6000 (300k context): 89.8 tok/s according to github.com (dataset as of Nov 3, 2026).
by jpezzulli
Intelligence (original model) · Artificial Analysis34with thinkingOriginal model's value. Heavily compressed (~2 bit), intelligence is likely much lower.
≤ 3 bit: quantization may cost quality
Engine
- Engine
- vLLM
- Quantization
- 2-bit W2-Experten (MoET-Planes) + 6 GiB FP4-Korrektur-Tier (512×12 MiB), FP8-MLA-KV; Basis offizielles MXFP4-Checkpoint
- Model family
- DeepSeek-V4-Flash
- Context
- 300,000
- Parameters
- 284B MoE
- Creator
- jpezzulli
- GitHub stars
- 17
- Repo updated
- Aug 19, 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
Prefill by context
What you need
- Hardware
- 1 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsdeepseek-ai/DeepSeek-V4-Flash-0731 MIT
- Engine
- vLLM
- Context
- 300,000 tokens
Notes
What matters before you rebuild it.
- ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
Sources
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.