4× RTX 3090
110tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- License unclear
Local AI · Recipe · 2× RTX 3090
Qwen3.8-Flash-Next 125B UD-Q4_K_XL with llama.cpp on 2× RTX 3090
by noonghunna
Engine
- Engine
- llama.cpp
- Quantization
- GGUF UD-Q4_K_XL, q8_0 KV
- Model family
- Qwen3.8-Flash-Next
- Context
- 204,800
- Parameters
- 125B MoE
- Creator
- noonghunna
- GitHub stars
- 2,288
- Repo updated
- Sep 25, 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 RTX 3090
- Weights
- Main weightsunsloth/Qwen3.8-Flash-Next-GGUF other
- Engine
- llama.cpp
- Context
- 204,800 tokens
Notes
What matters before you rebuild it.
- Partly in system RAM
- Experimental
- 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
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
26.4tok/sEveryday
1 request, prose prompt, with MTP (NEXTN) (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- 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.