Ministral 3 3B Instruct 2512 needs about 3.4 GB of memory at IQ4_XS (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 1.3 GB (IQ2_M) to 6.9 GB (F16). 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 instruction model
Ministral 3 3B Instruct 2512 is a 3.43B parameter model with a 256k context window. It includes a 0.4B vision encoder and supports multilingual instruction following. The model is edge‑optimized and licensed under Apache 2.0.
Good at
- Vision‑enabled instruction following
- Multilingual chat
- Agentic function calling
Limits
- Large context requires 256k tokens
- No dedicated vision hardware needed
- Requires 8k context for memory estimates
Best for
- Real‑time image captioning
- Low‑resource translation
- Fine‑tuning on edge devices
Who it’s for. Developers building lightweight, real‑time AI applications on edge or low‑resource hardware. The model is suitable for local deployment where VRAM is limited but a large context window is needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q2_K_L | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.2 GB | Fits | Get file → | |
| IQ4_XS | 2.1 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_XL | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_XL | 2.7 GB | 4.0 GB | Fits | Get file → | |
| Q6_K_L | 3.4 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 4.8 GB | 6.2 GB | Fits | Get file → | |
| F16 | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8GB VRAM, use IQ4_XS (file size 2.06 GB, estimated 3.4 GB memory) or Q4_K_XL (2.24 GB, 3.6 GB). For 4GB VRAM, IQ2_M (1.32 GB, 2.7 GB) or Q2_K_L (1.42 GB, 2.8 GB) are appropriate. Higher precision quants like Q8_0 or F16 require more than 6 GB VRAM.
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_XL (2.7 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (3.4 GB file, about 4.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.8 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 8.2 GB in use).
Which Ministral 3 3B Instruct 2512 quant should you choose?
IQ4_XS (2.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_M at 1.3 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 Ministral 3 3B Instruct 2512
How much VRAM does Ministral 3 3B Instruct 2512 need?
About 3.4 GB at IQ4_XS 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 4.8 GB file needs about 6.2 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: IQ2_M is 1.3 GB, Q2_K_L is 1.4 GB, IQ3_M is 1.6 GB, Q3_K_L is 1.8 GB, IQ4_XS is 2.1 GB, Q4_K_XL is 2.2 GB and 4 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 EnlistedGhost/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 IQ4_XS or Q4_K_XL quantizations will fit within 8 GB VRAM with estimated memory usage of 3.4–3.6 GB at 8k context.
Does this model support vision tasks?
Yes, it includes a 0.4B vision encoder and can analyze images alongside text.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.