bonchon needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.4 GB (Q4_K_M) to 4.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
8.03B Qwen2 model in GGUF format
Bonchon is an 8.03B parameter Qwen2 model released under the apache-2.0 license. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model is designed for general-purpose text generation.
Good at
- Large context handling
- Versatile text generation
- Open-source licensing
Limits
- No vision support
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Chat applications
- Text completion
- Research prototyping
Who it’s for. Developers and researchers who need a large‑parameter Qwen2 model in a lightweight GGUF format. The model is suitable for those who prefer open-source licensing and a 32768 token context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| — | 0.7 GB | 1.3 GB | Fits | Get file → | |
| — | 1.0 GB | 1.6 GB | Fits | Get file → | |
| — | 2.4 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 4.7 GB | Fits | Get file → | |
| — | 4.1 GB | 4.7 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 4.7 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.0 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.0 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.0 GB | Fits | Get file → | |
| — | 4.4 GB | 5.0 GB | Fits | Get file → | |
| — | 4.7 GB | 5.3 GB | Fits | Get file → | |
| — | 4.9 GB | 5.5 GB | Fits | Get file → |
For low‑memory setups, use the Q4_K_M quantization with a 0.4 GB file that requires about 1 GB of VRAM at 8k context. For higher quality, the 4.08 GB Q4_K_M file needs roughly 4.7 GB of VRAM. Memory estimates are approximate.
What GPU do you need for bonchon?
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: the best quant that fits is the main file (2.4 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (4.9 GB file, about 5.5 GB in use).
Which bonchon quant should you choose?
Q4_K_M is the usual starting point for bonchon: it balances file size and quality well. Here it is a 0.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bonchon
How much VRAM does bonchon need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 bonchon on an 8 GB GPU?
Yes, with the smaller files: the 4.9 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bonchon GGUF?
It depends on the quant: Q4_K_M is 0.4 GB, file is 0.7 GB, file is 1.0 GB, file is 2.4 GB, Q4_K_M is 4.1 GB, file is 4.1 GB and 7 more.
What context length does bonchon support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download bonchon GGUF?
The files are on Hugging Face in the llmware/bonchon repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does bonchon 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.
Can I run Bonchon on 8 GB VRAM?
Yes, the 0.4 GB Q4_K_M quantization uses about 1 GB of VRAM, well within an 8 GB budget. The larger 4.08 GB quantization uses about 4.7 GB, also feasible on 8 GB.
Is Bonchon suitable for vision tasks?
No, the model has no vision support and is intended for text generation only.
What license applies to Bonchon?
The model is released under the apache-2.0 license.