4× RTX 3090
145tok/sEveryday
1 request, prose prompt, with DFlash (per recipe) Source
Intelligence34with thinkingno thinking 20
- Experimental
Local AI · Recipe · 1× RTX 3090
Qwen3.8 27.3B with llama.cpp on 1× RTX 3090
Qwen3.8 27.3B with llama.cpp on 1× RTX 3090: 57 tok/s according to github.com (dataset as of Sep 29, 2026).
by alesha-pro
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- llama.cpp
- Quantization
- Mirai-S-Trellis 2.4-bit + q8_0 KV
- Model family
- Qwen3.8
- Context
- 131,072
- Parameters
- 27.3B dense (Mirai S: 2.4 bits/weight)
- Creator
- alesha-pro
- GitHub stars
- 10
- Repo updated
- Oct 7, 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
- 1 × NVIDIA RTX 3090
- Weights
- Main weightsalesha-pro/Qwen3.8-27B-S-mirai-GGUF Apache-2.0
- Basetrymirai/Qwen3.8-27B-S-experimental Apache-2.0
- Engine
- llama.cpp
- Context
- 131,072 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× DGX Spark
58.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
1× RTX 3090
57tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligenceno independent value
- Custom kernel required
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.