4× RTX 3090
110tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- License unclear
Local AI · Recipe · 1× DGX Spark
Qwen3.8-Flash-Next 80B UD-IQ4_XS with llama.cpp on 1× DGX Spark
Qwen3.8-Flash-Next 80B UD-IQ4_XS with llama.cpp on 1× DGX Spark: 26.9 tok/s according to github.com (dataset as of Sep 29, 2026).
by Weschera
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- llama.cpp
- Quantization
- Unsloth UD-IQ4_XS GGUF (94 GB)
- Model family
- Qwen3.8-Flash-Next
- Context
- 262,144
- Parameters
- 80B-Klasse hybrid SSM + sparse-attention MoE (README; ohne Params-Auflösung)
- Creator
- Weschera
- GitHub stars
- 9
- Repo updated
- Aug 27, 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 weightsunsloth/Qwen3.8-Flash-Next-GGUF other
- Engine
- llama.cpp
- Context
- 262,144 tokens
Related recipes
2× DGX Spark
54.4tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Access on request
- License unclear
1× DGX Spark
53tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
1× DGX Spark
48.7tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Access on request
- License unclear
2× DGX Spark
43.2tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
2× RTX 3090
36.8tok/sEveryday
1 request, prose prompt, with ngram Source
Intelligence40with thinking
- Partly in system RAM
- Experimental
- License unclear
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.