2× DGX Spark
54.4tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Access on request
- License unclear
Local AI · Recipe · 2× DGX Spark
DeepSeek-V4-Flash-Vision-Exp FP8 with vLLM on 2× DGX Spark
by r0b0tlab
32.5tok/sEveryday
1 request, prose prompt, with DSpark (adaptive verification) (per recipe)
Source: github.comIntelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM
- Quantization
- offizielle Gewichte + FP8 KV
- Model family
- DeepSeek-V4-Flash-Vision-Exp
- Context
- 1,048,576
- Creator
- r0b0tlab
- GitHub stars
- 5
- Repo updated
- Sep 3, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
No sourced measurements for this recipe.
What you need
- Hardware
- 2 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp MIT
- Engine
- vLLM
- Context
- 1,048,576 tokens
Notes
What matters before you rebuild it.
- Experimental
- Custom kernel required
Sources
Related recipes
2× DGX Spark
36.1tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- Non-commercial
- License unclear
2× DGX Spark
35tok/sEveryday
1 request, prose prompt, with EAGLE Source
Intelligenceno independent value
- Experimental
2× DGX Spark
33.2tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- Custom kernel required
2× DGX Spark
31.6tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
2× DGX Spark
31.6tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
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.