SMOLM2Prover 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 2 quants, from 0.3 GB (Q4_K_M) to 0.7 GB.
SMOLM2Prover – a 360M‑parameter reasoning‑focused Llama model in GGUF format
SMOLM2Prover is a 0.362‑billion‑parameter Llama architecture model fine‑tuned for reasoning tasks. It supports a 8192‑token context window and is released under the Apache‑2.0 license.
Good at
- Reasoning
- Compact size
- LLM inference with llama.cpp
Limits
- No vision support
- Requires 8192‑token context
- License is Apache‑2.0
Best for
- Chat‑based reasoning prompts
- Lightweight inference on edge devices
- Fine‑tuning on custom reasoning datasets
Who it’s for. Developers needing a small, reasoning‑oriented Llama model for on‑device inference. It is suitable for researchers and hobbyists working with llama.cpp or compatible runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 1.1 GB | Fits | Get file → | |
| — | 0.7 GB | 1.6 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_M quant (0.27 GB file, ~1.1 GB memory at 8k context) is recommended. If more memory is available, the unknown quant (0.73 GB file, ~1.6 GB memory) can be used for higher precision.
What GPU do you need for SMOLM2Prover?
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 SMOLM2Prover quant should you choose?
Q4_K_M is the usual starting point for SMOLM2Prover: it balances file size and quality well. Here it is a 0.3 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SMOLM2Prover
How much VRAM does SMOLM2Prover 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 SMOLM2Prover 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 SMOLM2Prover GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, file is 0.7 GB.
What context length does SMOLM2Prover 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 SMOLM2Prover GGUF?
The files are on Hugging Face in the reaperdoesntknow/SMOLM2Prover-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 SMOLM2Prover 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 SMOLM2Prover on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 1.1 GB of VRAM at 8k context, fitting comfortably in 8 GB.
Does this model support vision tasks?
No, SMOLM2Prover is a text‑only Llama model with no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.