Baguettotron needs about 1.2 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.2 GB (IQ4_XS) to 0.6 GB (F16).
321 M‑parameter small reasoning model
Baguettotron is a 321 million parameter decoder trained on 200 billion tokens from SYNTH. It is the deepest SLM in its size range with 80 layers and focuses on general reasoning, math, and retrieval tasks.
Good at
- General reasoning
- Arithmetic and simple math
- Retrieval‑augmented generation
Limits
- No vision support
- Requires at least 8 k context
- License is apache‑2.0
Best for
- Instruction following
- Creative writing
- Knowledge retrieval
Who it’s for. Developers needing a lightweight reasoning model for European languages. The model supports French, German, Italian, Spanish, Polish, Latin and Dutch, with reasoning traces in English.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 1.0 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.0 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.1 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 1.1 GB | Fits | Get file → | |
| BF16 | 0.6 GB | 1.4 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM use Q4_0 or IQ4_XS (0.2 GB file, ~1.2 GB memory). If 16 GB VRAM is available, Q4_K_M or Q5_K_M (0.24–0.26 GB file, ~1.2–1.3 GB memory) offer better quality. Larger quants like F16 or BF16 (0.64 GB file, ~1.6 GB memory) provide full precision but need more memory.
What GPU do you need for Baguettotron?
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 BF16 (0.6 GB file, about 1.6 GB in use).
Which Baguettotron quant should you choose?
Q4_K_M is the usual starting point for Baguettotron: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 GB, about 1.4 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 IQ4_XS at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Baguettotron
How much VRAM does Baguettotron need?
About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Baguettotron on an 8 GB GPU?
Yes, with BF16: the 0.6 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 Baguettotron GGUF?
It depends on the quant: IQ4_XS is 0.2 GB, Q4_0 is 0.2 GB, IQ4_NL is 0.2 GB, Q4_1 is 0.2 GB, Q4_K_S is 0.2 GB, Q4_K_M is 0.2 GB and 6 more.
What context length does Baguettotron support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.
Where can I download Baguettotron GGUF?
The files are on Hugging Face in the PleIAs/Baguettotron-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 Baguettotron 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 Baguettotron on 8 GB VRAM?
Yes, the 8‑bit Q4_0 or IQ4_XS variants use about 1.2 GB of VRAM at 8 k context, fitting comfortably in 8 GB.
Does Baguettotron support image input?
No, the model has no vision capabilities and is text‑only.
What languages can it understand?
It reads and writes French, German, Italian, Spanish, Polish, Latin and Dutch; reasoning traces are in English.