Mistral Small 3.1 DRAFT 0.5B needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.4 GB (IQ2_M) to 1.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
Mistral Small 3.1 DRAFT 0.5B – lightweight 0.593B‑parameter model
Mistral Small 3.1 DRAFT 0.5B is a 0.593B‑parameter model based on the qwen2 architecture. It was trained for 2 epochs on 20k unique examples, totaling 12 million tokens per epoch. The model supports up to 32768 context tokens and is released under the Apache‑2.0 license.
Good at
- Fast inference on modest GPUs
- Low memory footprint with quantization
- Supports 32k context length
Limits
- No vision capabilities
- No explicit language support list
- Requires llama.cpp or compatible runtime
Best for
- Rapid prototyping of instruction following
- Testing speculative decoding pipelines
- Running on edge devices with limited VRAM
Who it’s for. Developers and researchers who need a small, fast Mistral variant for experimentation or deployment on hardware with limited resources. The model is suitable for those who prefer open‑source licensing and a flexible quantization workflow.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ4_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ4_NL | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K_L | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_XL | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_L | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_L | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q6_K_L | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| BF16 | 1.2 GB | 1.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (0.4 GB file, ~1 GB memory). For 4 GB VRAM, choose Q3_K_S or Q3_K_M (0.39–0.4 GB file, ~1 GB memory). If memory is very tight, IQ2_M or IQ3_XXS (0.38 GB file, ~1 GB memory) are viable options. Memory estimates are approximate.
What GPU do you need for Mistral Small 3.1 DRAFT 0.5B?
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 (1.2 GB file, about 1.8 GB in use).
Which Mistral Small 3.1 DRAFT 0.5B quant should you choose?
Q4_K_M is the usual starting point for Mistral Small 3.1 DRAFT 0.5B: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.6 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 IQ2_M at 0.4 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 Mistral Small 3.1 DRAFT 0.5B
How much VRAM does Mistral Small 3.1 DRAFT 0.5B need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Mistral Small 3.1 DRAFT 0.5B on an 8 GB GPU?
Yes, with BF16: the 1.2 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mistral Small 3.1 DRAFT 0.5B GGUF?
It depends on the quant: IQ2_M is 0.4 GB, IQ3_XXS is 0.4 GB, Q3_K_S is 0.4 GB, IQ3_XS is 0.4 GB, Q2_K is 0.4 GB, IQ3_M is 0.4 GB and 18 more.
What context length does Mistral Small 3.1 DRAFT 0.5B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download Mistral Small 3.1 DRAFT 0.5B GGUF?
The files are on Hugging Face in the bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-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 Mistral Small 3.1 DRAFT 0.5B 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 4 GB VRAM?
Yes, by selecting a quantization such as Q3_K_S or IQ2_M, which use about 1 GB of VRAM at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.