Bonsai 8B llama.cpp needs about 4.1 GB of memory at TQ2_0 (a 2.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.4 GB (TQ2_0) to 3.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Bonsai 8B llama.cpp is a 8.19B-parameter Llama model in GGUF format, quantized by vinpix. Its trained context length is 64K tokens. The repository has 2 quant files, from 2.4 GB (TQ2_0) to 3.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ2_0 | 2.4 GB | 4.1 GB | Fits | Get file → | |
| — | 3.0 GB | 4.7 GB | Fits | Get file → |
What GPU do you need for Bonsai 8B llama.cpp?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (3.0 GB file, about 4.7 GB in use).
Which Bonsai 8B llama.cpp quant should you choose?
TQ2_0 (2.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bonsai 8B llama.cpp
How much VRAM does Bonsai 8B llama.cpp need?
About 4.1 GB at TQ2_0 with an 8K context window. That is the 2.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Bonsai 8B llama.cpp on an 8 GB GPU?
Yes, with the smaller files: the 3.0 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bonsai 8B llama.cpp GGUF?
It depends on the quant: TQ2_0 is 2.4 GB, file is 3.0 GB.
What context length does Bonsai 8B llama.cpp support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Bonsai 8B llama.cpp GGUF?
The files are on Hugging Face in the vinpix/Bonsai-8B-llama.cpp repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Bonsai 8B llama.cpp use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.