1× DGX Spark
71.8tok/sEveryday
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
Local AI · Recipe · 1× DGX Spark
Bonsai-27B Q4_K_M with llama.cpp on 1× DGX Spark
Bonsai-27B Q4_K_M with llama.cpp on 1× DGX Spark: 15.7 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by vcruz305
Intelligence (original model) · Artificial Analysisno independent value
≤ 3 bit: quantization may cost quality
Engine
- Engine
- llama.cpp 62061f91 (prism) / mainline cecbf5fb0
- Quantization
- GGUF Q4_K_M (imatrix); Ladder Q3_K_M–Q8_0
- Model family
- Bonsai-27B
- Context
- 16,384
- Parameters
- 27B dense
- Creator
- vcruz305
- GitHub stars
- 1
- Repo updated
- Jul 14, 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
What you need
- Hardware
- 1 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsvcruz305/Bonsai-27B-GGUF Apache-2.0
- Draft modelprism-ml/Bonsai-27B-gguf Apache-2.0
- Baseprism-ml/Bonsai-27B-gguf Apache-2.0
- Engine
- llama.cpp 62061f91 (prism) / mainline cecbf5fb0
- Context
- 16,384 tokens
Notes
What matters before you rebuild it.
- ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
Sources
Related recipes
1× DGX Spark
60.3tok/sEveryday
1 request, prose prompt (essay), context 2k, no drafter (per recipe) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
59.4tok/sEveryday
1 request, chat prompt (20 prompts, thinking off), no drafting (default profile) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
58.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- Custom kernel required
1× DGX Spark
55.6tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
1× DGX Spark
53.3tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Custom kernel required
- License unclear
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.