4× RTX 3090
110tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- License unclear
Local AI · Recipe · 1× RTX PRO 6000
Qwen3.8-Flash-Next 92.7B NVFP4 with vLLM on 1× RTX PRO 6000
Engine
- Engine
- vLLM
- Quantization
- NVFP4 Experten/PLE + MXFP8 Attention/Shared; FP8 KV (Messung), lil-Default BF16 KV
- Model family
- Qwen3.8-Flash-Next
- Context
- —
- Parameters
- ~92.7B (safetensors total); 512 Experten/10 aktiv
- Creator
- local-inference-lab
- GitHub stars
- 3
- Repo updated
- Sep 19, 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 PRO 6000 Blackwell
- Weights
- Main weightslocal-inference-lab/Qwen3.8-Flash-Next-NVFP4 other
- BaseQwen/Qwen3.8-Flash-Next other
- Engine
- vLLM
Notes
What matters before you rebuild it.
- Custom kernel required
- License unclear
Sources
- github.com/local-inference-lab/rtx6kpro/blob/master/models/qwen38-flash-next.md#measured-performance
- huggingface.co/local-inference-lab/lil-catalog/blob/main/Qwen3.8-Flash-Next-NVFP4/lil.yaml
- huggingface.co/local-inference-lab/Qwen3.8-Flash-Next-NVFP4
- github.com/local-inference-lab/rtx6kpro/blob/master/models/qwen38-flash-next.md
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.