SmolCompressor 360M needs about 1.2 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.7 GB (F16).
SmolCompressor 360M: Lightweight context compression for LLM pipelines
SmolCompressor 360M is a 360M parameter causal language model fine‑tuned for context compression and RAG pruning. It reduces verbose source text by about 70‑80 % while preserving all key facts, dates, names, and metrics. The model runs easily on a local CPU.
Good at
- Compresses long documents 70‑80 %
- Preserves all factual details
- Outputs structured JSON with entities
Limits
- No vision support
- Requires 8 k context for full performance
- License is apache‑2.0
Best for
- RAG pipeline preprocessing
- Meeting transcript summarization
- Search result pruning
Who it’s for. Developers building LLM pipelines who need a lightweight middleware to shrink large text chunks before feeding them to a heavier reasoning model. It is ideal for local CPU deployments and low‑budget GPU setups.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (0.39 GB file, ~1.2 GB memory at 8 k context). For 4 GB VRAM, use F16 (0.73 GB file, ~1.6 GB memory at 8 k context). Memory estimates are approximate.
What GPU do you need for SmolCompressor 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 F16 (0.7 GB file, about 1.6 GB in use).
Which SmolCompressor 360M quant should you choose?
Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SmolCompressor 360M
How much VRAM does SmolCompressor 360M need?
About 1.2 GB at Q8_0 with an 8K context window. That is the 0.4 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 SmolCompressor 360M on an 8 GB GPU?
Yes, with F16: 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 SmolCompressor 360M GGUF?
It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.7 GB.
What context length does SmolCompressor 360M support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.
Where can I download SmolCompressor 360M GGUF?
The files are on Hugging Face in the smoll-swarm/SmolCompressor-360M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SmolCompressor 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 SmolCompressor on 4 GB VRAM?
Yes, using the F16 quantized model which requires about 1.6 GB memory at 8 k context.
Does SmolCompressor support image input?
No, it only processes text and outputs JSON.
What license does SmolCompressor use?
The model is released under the apache‑2.0 license.