4× RTX 3090
110tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- License unclear
Local AI · Recipe · 1× RTX 5090
Qwen3.8-Flash-Next 125B-A10B UD-Q2_K_XL with llama.cpp on 1× RTX 5090
by notwitcheer
Intelligence (original model) · Artificial Analysis40with thinking
≤ 3 bit: quantization may cost quality
Engine
- Engine
- llama.cpp
- Quantization
- GGUF UD-Q2_K_XL (78.9 GB), Experten teilw. im RAM
- Model family
- Qwen3.8-Flash-Next
- Context
- —
- Parameters
- 125B MoE / 10B active
- Creator
- notwitcheer
- GitHub stars
- 40
- Repo updated
- Sep 20, 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
- 1 × NVIDIA RTX 5090
- Weights
- Main weightsunsloth/Qwen3.8-Flash-Next-GGUF other
- Engine
- llama.cpp
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.
- Partly in system RAM
- License unclear
Sources
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× RTX 3090
36.8tok/sEveryday
1 request, prose prompt, with ngram Source
Intelligence40with thinking
- Partly in system RAM
- Experimental
- 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
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.