Ministral 3 14B Instruct 2512 needs about 10.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 8.2 GB (Q4_K_M) to 27.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral 3 14B Instruct 2512 – a 14B vision‑enabled LLM for edge deployment
Ministral 3 14B Instruct 2512 is a 14 billion‑parameter model with a 0.4 billion‑parameter vision encoder. It supports a 256k context window and is fine‑tuned for instruction tasks. The model is available in multiple GGUF quantizations and is licensed under Apache 2.0.
Good at
- Vision and text understanding
- Multilingual instruction following
- Agentic function calling
Limits
- Large context requires 256k tokens
- No native vision support beyond image analysis
- Requires at least 24 GB VRAM in FP8
Best for
- Local chat assistants
- Edge‑based agentic workflows
- Fine‑tuning for specialized tasks
Who it’s for. Developers and organizations needing a compact, vision‑capable LLM that can run on consumer GPUs. The model is suitable for private AI deployments and local agentic applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 8.2 GB | 10.1 GB | Too big | Get file → | |
| Q5_K_M | 9.6 GB | 11.5 GB | Too big | Get file → | |
| Q8_0 | 14.4 GB | 16.2 GB | Too big | Get file → | |
| BF16 | 27.0 GB | 28.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (8.24 GB file, ~10.1 GB VRAM at 8 k context). For 16 GB VRAM use Q5_K_M (9.62 GB file, ~11.5 GB VRAM). For 24 GB VRAM use Q8_0 (14.36 GB file, ~16.2 GB VRAM).
What GPU do you need for Ministral 3 14B 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.6 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (9.6 GB file, about 11.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.4 GB file, about 16.2 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (27.0 GB file, about 28.9 GB in use).
Which Ministral 3 14B Instruct 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 14B Instruct 2512: it balances file size and quality well. Here it is a 8.2 GB file.
The Q8_0 file is 14.4 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 14B Instruct 2512
How much VRAM does Ministral 3 14B Instruct 2512 need?
About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.2 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 Ministral 3 14B Instruct 2512 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ministral 3 14B Instruct 2512 GGUF?
It depends on the quant: Q4_K_M is 8.2 GB, Q5_K_M is 9.6 GB, Q8_0 is 14.4 GB, BF16 is 27.0 GB.
What context length does Ministral 3 14B 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Ministral 3 14B Instruct 2512 GGUF?
The files are on Hugging Face in the mistralai/Ministral-3-14B-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 14B 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 Ministral 3 14B Instruct 2512 on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 10.1 GB VRAM at 8 k context, so 8 GB may be insufficient but could work with lower context.
Does the model support image input?
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.