1× DGX Spark
53tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
Local AI · Recipe · 1× DGX Spark
Spark-X2.5-4B BF16 with SGLang on 1× DGX Spark
Spark-X2.5-4B BF16 with SGLang on 1× DGX Spark: 21.8 tok/s according to github.com (dataset as of Sep 29, 2026).
by Weschera
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- SGLang
- Quantization
- BF16 (unquantisiert)
- Model family
- Spark-X2.5-4B
- Context
- 131,072
- Parameters
- 4B (Modellname)
- Creator
- Weschera
- GitHub stars
- 0
- Repo updated
- Sep 7, 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
- 1 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsXHToken/Spark-X2.5-4B Apache-2.0
- Engine
- SGLang
- Context
- 131,072 tokens
Related recipes
1× DGX Spark
48.7tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Access on request
- License unclear
1× DGX Spark
45tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligenceno independent value
1× DGX Spark
40.9tok/sEveryday
1 request, prose prompt, prompt 50 tokens, with DSpark (per recipe) Source
Intelligence25with thinking
- License unclear
1× DGX Spark
32tok/sEveryday
1 request, prose prompt, with Drafting aus dem Prompt (Edit-Setup, lt. README 'drafts its guesses from your prompt') (per recipe) Source
Intelligence40with thinking
- License unclear
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.