Bonsai GGUF models
79 GGUF models in the Bonsai family, quantized by 55 uploaders. Sizes run from 6M to 27.3B parameters. The longest trained context is 256K tokens.
About the Bonsai GGUF models
Bonsai is represented on ggufmodels.com by 79 GGUF models, quantized by 55 uploaders on Hugging Face. The most downloaded are Bonsai-27B, Bonsai-8B and Bonsai-1.7B. Parameter counts run from 6M to 27.3B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Bonsai model is between 1.1 to 16.5 GB, which is the quant most people start with. Most files come from mradermacher (8), Hagwell (4) and sinatras (3). The quants you will meet most often are Q1_0 (39), Q2_K (13), Q4_K_M (10) and Q8_0 (8), where the number is how many models offer that quant.
Frequently asked questions
Which Bonsai GGUF should I download?
The most downloaded Bonsai GGUF here is Bonsai-27B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Bonsai model need?
Q4_K_M files of Bonsai models on this site range from 1.1 to 16.5 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Bonsai GGUF files come from?
The most common quantizers here are mradermacher, Hagwell and sinatras. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.