4× RTX 3090
145tok/sEveryday
1 request, prose prompt, with DFlash (per recipe) Source
Intelligence34with thinkingno thinking 20
- Experimental
Local AI · Recipe · 1× RTX 5090
Qwen3.8 27B NVFP4 with vLLM on 1× RTX 5090
by MiaAI-Lab
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 20
Engine
- Engine
- vLLM 0.27.1 (+ PR #40914 Patch)
- Quantization
- NVFP4 + TurboQuant 4-bit KV
- Model family
- Qwen3.8
- Context
- 262,144
- Parameters
- 27B dense
- Creator
- MiaAI-Lab
- GitHub stars
- 87
- Repo updated
- Sep 23, 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 weightsRadixArk/Qwen3.8-27B-NVFP4 Apache-2.0
- Engine
- vLLM 0.27.1 (+ PR #40914 Patch)
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
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.