4× RTX 3090
145tok/sEveryday
1 request, prose prompt, with DFlash (per recipe) Source
Intelligence34with thinkingno thinking 20
- Experimental
Local AI · Recipe · 4× RTX PRO 6000
Qwen3.8 27B FP8 with vLLM on 4× RTX PRO 6000
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 20
Engine
- Engine
- vLLM
- Quantization
- FP8 (offiziell) + FP8 KV
- Model family
- Qwen3.8
- Context
- —
- Parameters
- 27B dense
- Creator
- local-inference-lab
- GitHub stars
- 1,101
- 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
- 4 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightsQwen/Qwen3.8-27B-FP8 Apache-2.0
- Engine
- vLLM
Related recipes
2× RTX 3090
123tok/sEveryday
1 request, prose prompt, with Draft Source
Intelligence34with thinkingno thinking 20
4× RTX 3090
85.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
2× RTX 3090
76.4tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 20
1× RTX 3090
42.8tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence34with thinkingno thinking 20
1× RTX 3090
39.7tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence34with thinkingno thinking 20
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.