llavon ime llama 250m needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.1 GB (Q2_K) to 0.5 GB (F16).
Llavon IME LLaMA 250M – Bopomofo to Traditional Chinese conversion
Llavon IME LLaMA 250M is a small decoder‑only LLaMA‑style model trained for Traditional Chinese Bopomofo IME conversion. It predicts Traditional Chinese characters from Bopomofo input and is intended for local Windows IME inference.
Good at
- Bopomofo to Traditional Chinese conversion
- Local IME inference
- Custom vocabulary handling
Limits
- Context length 384 tokens
- No general chat capability
- CC‑BY‑NC‑4.0 license for non‑commercial use
Best for
- Windows IME integration
- macOS and Linux IME projects
- Local Bopomofo input tools
Who it’s for. Developers building local input method editors for Traditional Chinese. The model is suitable for applications that require quick, on‑device conversion from Bopomofo to Chinese characters without internet access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ3_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.5 GB | 1.0 GB | Fits | Get file → |
For 8 GB VRAM, Q2_K (0.1 GB) or IQ3_M (0.12 GB) provide the lowest memory usage. Q3_K_M (0.13 GB) and Q4_K_M (0.15 GB) offer slightly higher quality with still modest memory. F16 (0.5 GB) gives the best precision but needs more VRAM.
What GPU do you need for llavon ime llama 250m?
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 F16 (0.5 GB file, about 1.7 GB in use).
Which llavon ime llama 250m quant should you choose?
Q4_K_M is the usual starting point for llavon ime llama 250m: it balances file size and quality well. Here it is a 0.2 GB file.
If memory is tight, the smallest file is Q2_K at 0.1 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 llavon ime llama 250m
How much VRAM does llavon ime llama 250m need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 llavon ime llama 250m on an 8 GB GPU?
Yes, with F16: the 0.5 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llavon ime llama 250m GGUF?
It depends on the quant: Q2_K is 0.1 GB, IQ3_M is 0.1 GB, Q3_K_M is 0.1 GB, Q4_K_M is 0.2 GB, F16 is 0.5 GB.
What context length does llavon ime llama 250m support?
The GGUF header lists a trained context length of 384 tokens (384). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.0 GB at 384.
Where can I download llavon ime llama 250m GGUF?
The files are on Hugging Face in the tony65535/llavon-ime-llama-250m-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 llavon ime llama 250m use?
Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 4 GB VRAM?
Yes, the Q2_K and IQ3_M quantizations are under 0.2 GB file size and use about 1.3 GB VRAM at 8k context, fitting within 4 GB VRAM.
Does this model support vision or audio?
No, it is a decoder‑only language model with no vision or audio capabilities.
Is the model free for commercial use?
No, the weights are licensed CC‑BY‑NC‑4.0, allowing only non‑commercial use.