gguf sharded Llama 160M Chat v1 needs about 1.1 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.7 GB (F32).
Sharded Llama 160M Chat model in GGUF format
The gguf sharded Llama 160M Chat v1 model is a 0.162 billion‑parameter Llama architecture trained on 2048 context tokens. It is distributed in 12 quantized shards and licensed under apache‑2.0.
Good at
- Chat‑style conversations
- Lightweight inference
- Easy sharding
Limits
- No vision support
- Requires 8 k context for estimates
- License is apache‑2.0
Best for
- Local chatbot deployment
- Educational demos
- Rapid prototyping
Who it’s for. Developers needing a small, chat‑optimized Llama model that can run on modest hardware. The sharded GGUF format allows flexible deployment across different systems.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB (3 parts) | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB (4 parts) | 0.7 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB (4 parts) | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB (4 parts) | 0.7 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB (7 parts) | 0.8 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB (9 parts) | 0.8 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB (9 parts) | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB (9 parts) | 0.9 GB | Fits | Get file → | |
| F16 | 0.3 GB (7 parts) | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.3 GB (10 parts) | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB (12 parts) | 1.0 GB | Fits | Get file → | |
| F32 | 0.7 GB (7 parts) | 1.2 GB | Fits | Get file → |
For 8 GB VRAM, Q4_0 or Q4_K_S (0.16 GB file, ~1 GB memory) are suitable. For 4 GB VRAM, Q2_K (0.14 GB file, ~0.9 GB memory) is recommended. Larger models like Q8_0 need ~1.2 GB memory and 0.39 GB file.
What GPU do you need for gguf sharded Llama 160M Chat v1?
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 F32 (0.7 GB file, about 1.5 GB in use).
Which gguf sharded Llama 160M Chat v1 quant should you choose?
Q4_K_M is the usual starting point for gguf sharded Llama 160M Chat v1: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.4 GB, about 1.5 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 gguf sharded Llama 160M Chat v1
How much VRAM does gguf sharded Llama 160M Chat v1 need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.3 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 gguf sharded Llama 160M Chat v1 on an 8 GB GPU?
Yes, with F32: the 0.7 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gguf sharded Llama 160M Chat v1 GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_M is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB, Q3_K_S is 0.2 GB, Q4_K_M is 0.3 GB and 6 more.
What context length does gguf sharded Llama 160M Chat v1 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 gguf sharded Llama 160M Chat v1 GGUF?
The files are on Hugging Face in the Felladrin/gguf-sharded-Llama-160M-Chat-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does gguf sharded Llama 160M Chat v1 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 this model on 8 GB VRAM?
Yes, Q4_0 or Q4_K_S shards use about 1 GB memory at 8 k context, fitting within 8 GB VRAM.
How many shards are needed for inference?
The model is split into 3 to 12 shards depending on quant; all must be loaded for full inference.
Is this model suitable for vision tasks?
No, the model has no vision capabilities and is designed only for text.