1× DGX Spark
27.8tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence34with thinkingno thinking 20
- License unclear
Local AI · Recipe · 1× RTX 3090
Qwen3.8-27B EXL3 4.00 bpw with buun-llama-cpp on 1× RTX 3090
by r0b0tlab
27.8tok/sMixed
1 request, mixed prompt set, context 150000, with DFlash2 (per recipe)
Source: github.comIntelligence (original model) · Artificial Analysis34with thinkingno thinking 20
Engine
- Engine
- buun-llama-cpp
- Quantization
- EXL3 4.00 bpw (Target + DFlash2-Draft), VBR-KV turbo8/turbo3
- Model family
- Qwen3.8-27B
- Context
- 262,144
- Parameters
- 27B dense
- Creator
- r0b0tlab
- GitHub stars
- 4
- Repo updated
- Sep 20, 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 3090
- Weights
- Main weightsr0b0tlab/Qwen3.8-27B-EXL3-4.00bpw Apache-2.0
- Draft modelr0b0tlab/Qwen3.8-27B-DFlash2-EXL3-4.00bpw Apache-2.0
- Engine
- buun-llama-cpp
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
Related recipes
1× DGX Spark
23.5tok/sMixed
1 request, mixed prompt set, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
- License unclear
1× RTX 5090
224tok/sPeak
1 request, code prompt Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
1× RTX 3090
168tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence17with thinkingno thinking 13
1× RTX 3090
113tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
1× RTX 3090
59.7tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with 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.