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× DGX Spark
DeepSeek-V4-Flash 180B IQ2_XXS with DwarfStar on 1× DGX Spark
DeepSeek-V4-Flash 180B IQ2_XXS with DwarfStar on 1× DGX Spark: 13.6 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by 0xSero
Intelligence (original model) · Artificial Analysisno independent value
≤ 3 bit: quantization may cost quality
Engine
- Engine
- DS4 (antirez/ds4)
- Quantization
- Q2-REAP-ds4 (IQ2_XXS gate/up, Q2_K down, Q8_0 shared/attn)
- Model family
- DeepSeek-V4-Flash
- Context
- 200,000
- Parameters
- 180B (REAP K160)
- Creator
- 0xSero
- GitHub stars
- 14
- Repo updated
- May 30, 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 DGX Spark (GB10)
- Weights
- Main weights0xSero/DeepSeek-V4-Flash-180B-GGUF MIT
- Base0xSero/DeepSeek-V4-Flash-180B MIT
- Engine
- DS4 (antirez/ds4)
- Context
- 200,000 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.
- REAP-pruned
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.