Llama 3.2 Chibi 3B needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.4 GB (Q2_K) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llama 3.2 Chibi 3B – a 3.21 B‑parameter Japanese‑focused LLM
Llama 3.2 Chibi 3B is a 3.21 B‑parameter model trained on Japanese datasets. It is not fine‑tuned for chat and may need further tuning for conversational use. The model supports a 131 072‑token context window.
Good at
- Japanese language modeling
- Low‑resource deployment
- General language tasks
Limits
- No vision support
- Not fine‑tuned for chat
- Requires additional fine‑tuning for dialogue
Best for
- Edge devices with limited GPU
- Real‑time Japanese text generation
- Pre‑training for downstream Japanese tasks
Who it’s for. Developers building Japanese language applications on devices with limited memory. Researchers needing a small Japanese LLM for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| F16 | 6.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM use Q4_K_M (est. 3.5 GB) or Q3_K_M (est. 3.1 GB). For 12 GB VRAM use Q5_K_M (est. 3.8 GB). For 16 GB VRAM use Q6_K (est. 4.1 GB). File sizes range from 1.36 GB (Q2_K) to 6.43 GB (F16).
What GPU do you need for Llama 3.2 Chibi 3B?
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 Q5_K_M (2.3 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).
Which Llama 3.2 Chibi 3B quant should you choose?
Q4_K_M is the usual starting point for Llama 3.2 Chibi 3B: it balances file size and quality well. Here it is a 2.0 GB file.
The Q8_0 file is 3.4 GB, about 1.7 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 Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3.2 Chibi 3B
How much VRAM does Llama 3.2 Chibi 3B need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Llama 3.2 Chibi 3B on an 8 GB GPU?
Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3.2 Chibi 3B GGUF?
It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.7 GB, Q3_K_L is 1.8 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.9 GB and 6 more.
What context length does Llama 3.2 Chibi 3B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Llama 3.2 Chibi 3B GGUF?
The files are on Hugging Face in the mradermacher/Llama-3.2-Chibi-3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Llama 3.2 Chibi 3B use?
Hugging Face lists the license as llama3.2. 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 Llama 3.2 Chibi 3B on 8 GB VRAM?
Yes, use Q4_K_M or Q3_K_M quantizations, which estimate 3.5 GB and 3.1 GB memory usage at 8 k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
Is the model fine‑tuned for chat?
No, it is only pre‑trained for general language modeling and may need fine‑tuning for chat.