1× RTX 3090
168tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence17with thinkingno thinking 13
Local AI · Recipe · 1× RTX 3090
Gemma 4 31B with beellama.cpp on 1× RTX 3090
by noonghunna
Intelligence (original model) · Artificial Analysis19with thinkingno thinking 14
Engine
- Engine
- beellama.cpp (llama.cpp-Fork) v0.3.2-preview
- Quantization
- GGUF, q5_0/q4_1 KV
- Model family
- Gemma 4
- Context
- 131,072
- Parameters
- 31B dense
- Creator
- noonghunna
- GitHub stars
- 2,288
- 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
- 1 × NVIDIA RTX 3090
- Weights
- Main weightsunsloth/gemma-4-31B-it-GGUF Apache-2.0
- Draft modelAnbeeld/gemma-4-31B-it-DFlash-GGUF Apache-2.0
- Engine
- beellama.cpp (llama.cpp-Fork) v0.3.2-preview
- Context
- 131,072 tokens
Notes
What matters before you rebuild it.
- Community, experimental
Sources
Related recipes
1× RTX 5090
53tok/sPeak
1 request, synthetic prompt Source
Intelligence19with thinkingno thinking 14
1× DGX Spark
29.8tok/sPeak
1 request, best value reported by source 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
1× RTX 3090
50.3tok/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.