SmolLM 360M needs about 1.1 GB of memory at Q4_K (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.2 GB (IQ2_XXS) to 0.7 GB.
SmolLM 360M – a compact 360M‑parameter instruction model
SmolLM 360M is a 360M‑parameter language model built on the llama architecture. It is trained on the SmolLM‑Corpus and fine‑tuned for instruction following. The model supports up to 2048 context tokens and is released under the apache‑2.0 license.
Good at
- Instruction following
- General knowledge queries
- Basic Python programming
Limits
- English only
- Limited arithmetic accuracy
- No vision support
Best for
- Local chatbot deployments
- Educational content generation
- Lightweight code assistance
Who it’s for. Developers and researchers needing a small, instruction‑oriented model for local inference. The model is suitable for projects with limited GPU memory and a focus on English language tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ2_XXS | 0.2 GB (5 parts) | 0.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB (5 parts) | 0.8 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB (5 parts) | 0.8 GB | Fits | Get file → | |
| Q4_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_K | 0.3 GB (6 parts) | 0.9 GB | Fits | Get file → | |
| Q5_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K | 0.3 GB (6 parts) | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q6_K | 0.4 GB (8 parts) | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB (8 parts) | 1.0 GB | Fits | Get file → | |
| — | 0.7 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, use IQ2_XXS (0.21 GB) or IQ3_XXS (0.21 GB). For 12 GB VRAM, Q4_K (0.27 GB) or Q5_K (0.29 GB) provide a good balance of size and quality. Higher‑precision Q6_K (0.37 GB) or Q8_0 (0.39 GB) are available if memory allows.
What GPU do you need for SmolLM 360M?
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 (0.7 GB file, about 1.6 GB in use).
Which SmolLM 360M quant should you choose?
Q4_K (0.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_XXS at 0.2 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
Frequently asked questions about SmolLM 360M
How much VRAM does SmolLM 360M need?
About 1.1 GB at Q4_K 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 SmolLM 360M on an 8 GB GPU?
Yes, with the smaller files: the 0.7 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolLM 360M GGUF?
It depends on the quant: IQ2_XXS is 0.2 GB, IQ2_XXS is 0.2 GB, IQ3_XXS is 0.2 GB, IQ3_XXS is 0.2 GB, IQ4_XS is 0.2 GB, IQ4_XS is 0.2 GB and 9 more.
What context length does SmolLM 360M 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 SmolLM 360M GGUF?
The files are on Hugging Face in the Felladrin/gguf-smollm-360M-instruct-add-basics repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SmolLM 360M 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 SmolLM 360M on 8 GB VRAM?
Yes, the IQ2_XXS and IQ3_XXS quantizations are under 1 GB of VRAM at 8k context, making them suitable for 8 GB GPUs.
Does the model support multiple languages?
The model is English only; it may struggle with non‑English prompts.
What context length does the model support?
The model is trained for up to 2048 context tokens.