Ministral 3 3B Instruct 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 25 quants, from 0.0 GB to 6.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Ministral 3 3B Instruct 2512 – a compact vision‑enabled LLM
Ministral 3 3B Instruct 2512 is a 3.43 billion‑parameter model with a 256k context window. It includes a 0.4 billion‑parameter vision encoder and supports instruction‑based tasks. The model is edge‑optimized and licensed under Apache 2.0.
Good at
- Vision‑enabled text generation
- Instruction following
- Multilingual support
Limits
- Large context window requires high VRAM
- No dedicated vision‑only mode
- Requires quantization for low‑memory devices
Best for
- Real‑time image captioning
- Low‑resource chatbots
- Fine‑tuning for specialized tasks
Who it’s for. Developers building lightweight, real‑time applications on edge or low‑resource devices. The model is suitable for embedded systems that need vision and instruction capabilities without large GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ2_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 2.8 GB | Fits | Get file → | |
| Q2_K | 1.5 GB | 2.8 GB | Fits | Get file → | |
| Q2_K_L | 1.6 GB | 2.9 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 3.0 GB | Fits | Get file → | |
| IQ3_M | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_XL | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 3.4 GB | Fits | Get file → | |
| IQ4_NL | 2.1 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 2.1 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_L | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_L | 2.6 GB | 3.9 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 4.2 GB | Fits | Get file → | |
| Q6_K_L | 2.9 GB | 4.3 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, estimated 3.5 GB memory). For 4 GB VRAM, use Q3_K_S (1.64 GB, 3 GB memory). For 2 GB VRAM, use IQ2_M (1.32 GB, 2.7 GB memory).
What GPU do you need for Ministral 3 3B Instruct 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_L (2.6 GB file, about 3.9 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 Instruct 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 3B Instruct 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.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Ministral 3 3B Instruct 2512
How much VRAM does Ministral 3 3B Instruct 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 Instruct 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 Instruct 2512 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.3 GB, IQ3_XXS is 1.4 GB, Q2_K is 1.5 GB, Q2_K_L is 1.6 GB, IQ3_XS is 1.6 GB and 19 more.
What context length does Ministral 3 3B Instruct 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 Instruct 2512 GGUF?
The files are on Hugging Face in the bartowski/mistralai_Ministral-3-3B-Instruct-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 Instruct 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 a quant like Q4_K_M or Q3_K_S will fit within 8 GB VRAM, with estimated memory usage around 3.5 GB.
Does the model support vision tasks?
Yes, it includes a 0.4 billion‑parameter vision encoder for image analysis.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.