Ministral 3 3B Reasoning 2512 needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.1 GB (Q4_K_M) to 6.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Ministral 3 3B Reasoning 2512 – a small, vision‑capable LLM for edge deployment
Ministral 3 3B Reasoning 2512 is a 3.43 billion‑parameter model with a 256k context window. It includes a 0.4 billion‑parameter vision encoder and is optimized for reasoning tasks such as math, coding and STEM. The model runs locally on a range of hardware, fitting in 16 GB VRAM in BF16 and under 8 GB when quantized.
Good at
- Reasoning and multi‑step problem solving
- Vision analysis and image captioning
- Agentic function calling and JSON output
Limits
- Large context requires 256k tokens
- No explicit language list provided
- Requires Apache 2.0 license compliance
Best for
- Real‑time edge inference
- Math and coding problem solving
- Vision‑enabled captioning
Who it’s for. Developers building lightweight, real‑time AI on edge or low‑resource devices. The model is suitable for applications that need reasoning, vision, and multilingual support within a small memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 5.0 GB | Fits | Get file → | |
| BF16 | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.15 GB, ~3.5 GB memory at 8k context) or Q5_K_M (2.47 GB, ~3.8 GB). For 16 GB VRAM, BF16 (6.87 GB, ~8.2 GB) provides full precision. Memory estimates are approximate.
What GPU do you need for Ministral 3 3B Reasoning 2512?
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 Q5_K_M (2.5 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 8.2 GB in use).
Which Ministral 3 3B Reasoning 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 3B Reasoning 2512: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.7 GB, about 1.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ministral 3 3B Reasoning 2512
How much VRAM does Ministral 3 3B Reasoning 2512 need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Ministral 3 3B Reasoning 2512 on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 3B Reasoning 2512 GGUF?
It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.5 GB, Q8_0 is 3.7 GB, BF16 is 6.9 GB.
What context length does Ministral 3 3B Reasoning 2512 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Ministral 3 3B Reasoning 2512 GGUF?
The files are on Hugging Face in the mistralai/Ministral-3-3B-Reasoning-2512-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 Ministral 3 3B Reasoning 2512 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 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations keeps memory below 8 GB.
Does it support vision tasks?
Yes, it includes a 0.4 billion‑parameter vision encoder for image analysis.
What license does it use?
Apache 2.0, allowing commercial and non‑commercial use and modification.