public models needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 0.1 GB (Q4_0) to 5.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
4.63B Qwen-3.5 LLM with reasoning, tools, and vision support
The public models collection offers a 4.63B parameter Qwen-3.5 architecture. It supports reasoning, tool usage, and vision tasks. Models are released under the MIT license and are available in multiple quantizations.
Good at
- Reasoning
- Tool integration
- Vision tasks
Limits
- No vision support in all quantizations
- Large memory requirement for high precision quants
- No mixture of experts
Best for
- Local OCR and document processing
- Multimodal vision-language tasks
- Tool‑enabled reasoning workflows
Who it’s for. Developers and researchers needing a versatile, open‑source LLM for offline deployment. The models are lightweight enough for edge devices while retaining vision and tool capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.1 GB | 1.6 GB | Fits | Get file → | |
| — | 1.3 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_XL | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_0 | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.4 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_0 (0.06 GB) or Q4_K_XL (2.62 GB). For 12 GB VRAM, Q4_K_M (2.71 GB) or Q8_0 (3.65 GB) are suitable. Higher precision quants like Q5_K_M (5.85 GB) require 16 GB or more.
What GPU do you need for public models?
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 (1.3 GB file, about 2.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.4 GB in use).
Which public models quant should you choose?
Q4_K_M is the usual starting point for public models: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 3.7 GB, about 1.3 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about public models
How much VRAM does public models need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 public models on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of public models GGUF?
It depends on the quant: Q4_0 is 0.1 GB, file is 1.3 GB, Q4_K_XL is 2.6 GB, Q4_K_M is 2.7 GB, Q4_0 is 3.3 GB, Q8_0 is 3.7 GB and 7 more.
What context length does public models support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download public models GGUF?
The files are on Hugging Face in the motgame/public_models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does public models use?
Hugging Face lists the license as mit. 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 Q4_0 on 8 GB VRAM?
Yes, Q4_0 uses 1.6 GB at 8k context, well within 8 GB VRAM limits.
What is the memory usage of Q8_0?
Q8_0 estimates 5.2 GB at 8k context, so a 12 GB VRAM setup is recommended.
Does this model support vision?
Yes, the model has detected vision abilities, but no dedicated vision-only quant is listed.