4× DGX Spark
46tok/sEveryday
1 request, prose prompt, with DSpark Source
Intelligenceno independent value
Local AI · Recipe · 4× RTX PRO 6000
DeepSeek-V4-Flash NVFP4 with vLLM on 4× RTX PRO 6000
DeepSeek-V4-Flash NVFP4 with vLLM on 4× RTX PRO 6000: 235 tok/s according to github.com (dataset as of Nov 3, 2026).
by Infatoshi
Engine
- Engine
- vLLM 0.26.1rc1.dev303+g74295e3bd
- Quantization
- NVFP4 (Experten; Marlin W4A16), fp8 KV (block 256)
- Model family
- DeepSeek-V4-Flash
- Context
- 262,144
- Creator
- Infatoshi
- GitHub stars
- 15
- Repo updated
- Aug 25, 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
- 4 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsMJPansa/DeepSeek-V4-Flash-0731-NVFP4 MIT
- Engine
- vLLM 0.26.1rc1.dev303+g74295e3bd
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
- github.com/Infatoshi/dsv4-flash-2x-rtxpro6000s/blob/main/docs/4X-RTX-PRO-6000.md#serve-flags-that-were-wrong-then-fixed
- github.com/Infatoshi/dsv4-flash-2x-rtxpro6000s
- github.com/Infatoshi/dsv4-flash-2x-rtxpro6000s/blob/main/docs/4X-RTX-PRO-6000.md
- github.com/Infatoshi/dsv4-flash-2x-rtxpro6000s/blob/main/scripts/serve_256k_tp4.sh
Related recipes
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
1× Mac
28.5tok/sEveryday
1 request, prose prompt, context 32k, with DSpark (per recipe) Source
Intelligenceno independent value
- ≤ 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.