2× RTX 3090Qwen3.8-27B (ThinkingCap-Finetune)
108tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligenceno independent value
- Experimental
- Custom kernel required
- License unclear
Local AI · Recipe · 2× RTX 3090
Qwen3.8-27B W4A8 with vLLM on 2× RTX 3090 (with MTP)
Qwen3.8-27B W4A8 with vLLM on 2× RTX 3090 (with MTP): 74 tok/s according to github.com (dataset as of Nov 3, 2026).
by noonghunna
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM v0.30.0
- Quantization
- AutoRound W4A16 INT4, serviert W4A8; fp8_e4m3 KV
- Model family
- Qwen3.8-27B (ThinkingCap-Finetune)
- Context
- 262,144
- Parameters
- 27B dense
- Creator
- noonghunna
- GitHub stars
- 2,471
- Repo updated
- Nov 2, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
Prefill by context
What you need
- Hardware
- 2 × NVIDIA RTX 3090
- Weights
- Main weightswasifb/ThinkingCap-Qwen3.8-27B-AutoRound-W4A16 other
- Engine
- vLLM v0.30.0
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Experimental
- License unclear
Sources
Related recipes
2× RTX 3090
199tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
2× RTX 3090
187tok/sEveryday
1 request, prose prompt, prompt 450 tokens, no speculative decoding Source
Intelligenceno independent value
2× RTX 3090
179tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
2× RTX 3090
151tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
2× RTX 3090
144tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
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.