Ministral 3 14B Instruct 2512 DASHQ Q2 needs about 6.5 GB of memory at IQ2_XS (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 4.1 GB (IQ2_XXS) to 5.4 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral 3 14B Instruct 2512 DASHQ Q2 – 13.5B language model with vision and instruction fine‑tuning
Ministral 3 14B Instruct 2512 is a 13.5B parameter model with a 0.4B vision encoder. It supports a 262144 token context window and is fine‑tuned for instruction tasks. The model is released under Apache‑2.0 and is available in several 2‑bit GGUF quantizations.
Good at
- Instruction following
- Vision analysis
- Agentic function calling
Limits
- No vision support in GGUF files
- Large context requires 256k tokens
- Requires recent llama.cpp build
Best for
- Local chat assistants
- Edge AI deployments
- Multilingual instruction handling
Who it’s for. Developers building private AI assistants that need instruction following and vision capabilities on modest hardware. The model is suitable for users who prefer an open‑source solution with a permissive license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 4.1 GB | 5.9 GB | Fits | Get file → | |
| IQ2_XS | 4.6 GB | 6.5 GB | Fits | Get file → | |
| IQ2_M | 4.9 GB | 6.8 GB | Fits | Get file → | |
| Q2_K_XL | 5.4 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM use IQ2_XXS (4.06 GB file, 5.9 GB memory at 8k context). For 12 GB VRAM use IQ2_XS (4.62 GB file, 6.5 GB memory). For 16 GB VRAM use IQ2_M (4.92 GB file, 6.8 GB memory). The Q2_K_XL quant (5.37 GB file, 7.2 GB memory) fits in 24 GB VRAM.
What GPU do you need for Ministral 3 14B Instruct 2512 DASHQ Q2?
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: the best quant that fits is IQ2_XXS (4.1 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_XL (5.4 GB file, about 7.2 GB in use).
Which Ministral 3 14B Instruct 2512 DASHQ Q2 quant should you choose?
IQ2_XS (4.6 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 4.1 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 14B Instruct 2512 DASHQ Q2
How much VRAM does Ministral 3 14B Instruct 2512 DASHQ Q2 need?
About 6.5 GB at IQ2_XS with an 8K context window. That is the 4.6 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 DASHQ Q2 on an 8 GB GPU?
Yes, with Q2_K_XL: the 5.4 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 14B Instruct 2512 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 4.1 GB, IQ2_XS is 4.6 GB, IQ2_M is 4.9 GB, Q2_K_XL is 5.4 GB.
What context length does Ministral 3 14B Instruct 2512 DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/Ministral-3-14B-Instruct-2512-DASHQ-Q2-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 DASHQ Q2 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, the IQ2_XXS quant file is 4.06 GB and requires about 5.9 GB memory at 8k context, which fits in 8 GB VRAM.
Does the GGUF version include vision?
No, the GGUF files contain only text; the vision tower is not included.
What license applies to this model?
The model is released under Apache‑2.0, allowing commercial and non‑commercial use.