Llama 160m needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.1 GB (Q2_K) to 0.2 GB (Q8_0).
Llama 160m – a small 160M‑parameter LLaMA‑style model
Llama 160m is a 160M‑parameter model trained on Wikipedia and portions of C4-en and C4‑realnewslike. It is available in multiple GGUF quantizations and is licensed under apache‑2.0.
Good at
- Lightweight inference
- Fast token generation
- Low VRAM usage
Limits
- No vision support
- Limited context to 2048 tokens
- No evaluation data
Best for
- Embedded devices
- Rapid prototyping
- Low‑cost text generation
Who it’s for. Developers needing a small, fast LLaMA‑style model for local inference. Suitable for edge devices or quick experimentation where full‑size models are impractical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_1 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_1 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 0.7 GB | Fits | Get file → |
For 8 GB VRAM, Q4_0 or Q4_K_S are suitable, each using about 0.9 GB memory at 8 k context. If more VRAM is available, Q5_0 or Q5_K_M provide higher quality with similar memory usage. Q8_0 uses 1 GB memory and offers the highest precision.
What GPU do you need for Llama 160m?
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 Q8_0 (0.2 GB file, about 1.0 GB in use).
Which Llama 160m quant should you choose?
Q4_K_M is the usual starting point for Llama 160m: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.2 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 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 Llama 160m
How much VRAM does Llama 160m need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 160m on an 8 GB GPU?
Yes, with Q8_0: the 0.2 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 160m GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 8 more.
What context length does Llama 160m support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.
Where can I download Llama 160m GGUF?
The files are on Hugging Face in the QuantFactory/llama-160m-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 160m 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 Llama 160m on 8 GB VRAM?
Yes, quantizations such as Q4_0 or Q4_K_S use approximately 0.9 GB memory at 8 k context, fitting within 8 GB VRAM.
Does Llama 160m support image input?
No, the model has no vision capabilities.
What license applies to Llama 160m?
The model is released under the apache‑2.0 license.