Ministral 3 8B Instruct 2512 DASHQ Q2 needs about 4.6 GB of memory at IQ2_XS (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.6 GB (IQ2_XXS) to 3.4 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Ministral 3 8B Instruct 2512 DASHQ Q2 – efficient 8.49B model with vision and instruction support
Ministral 3 8B Instruct 2512 is an 8.49B parameter model with a 256k context window. It includes a 0.4B vision encoder and supports instruction following, function calling, and JSON output. The model is edge‑optimized and licensed under Apache‑2.0.
Good at
- Instruction‑driven chat
- Vision‑enabled image analysis
- Low‑bit quantization for edge deployment
Limits
- No vision tower in GGUF files
- Requires 8k context for memory estimates
- Large context window may exceed VRAM on low‑end GPUs
Best for
- Local chat assistants
- Embedded AI in constrained devices
- Image description tasks
Who it’s for. Developers building local or embedded AI solutions that need a small, versatile model with vision and instruction capabilities. The model is suitable for both commercial and non‑commercial use under the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 2.6 GB | 4.3 GB | Fits | Get file → | |
| IQ2_XS | 3.0 GB | 4.6 GB | Fits | Get file → | |
| IQ2_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_XL | 3.4 GB | 5.1 GB | Fits | Get file → |
For 8GB VRAM, use IQ2_XXS (file size 2.64 GB, estimated 4.3 GB at 8k context). If 12GB VRAM is available, IQ2_XS (3 GB, 4.6 GB) or IQ2_M (3.17 GB, 4.8 GB) can be used. For the highest compression, Q2_K_XL (3.44 GB, 5.1 GB) is suitable on GPUs with 12GB+ VRAM.
What GPU do you need for Ministral 3 8B 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 Q2_K_XL (3.4 GB file, about 5.1 GB in use).
Which Ministral 3 8B Instruct 2512 DASHQ Q2 quant should you choose?
IQ2_XS (3.0 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 2.6 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 8B Instruct 2512 DASHQ Q2
How much VRAM does Ministral 3 8B Instruct 2512 DASHQ Q2 need?
About 4.6 GB at IQ2_XS with an 8K context window. That is the 3.0 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 8B Instruct 2512 DASHQ Q2 on an 8 GB GPU?
Yes, with Q2_K_XL: the 3.4 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 8B Instruct 2512 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 2.6 GB, IQ2_XS is 3.0 GB, IQ2_M is 3.2 GB, Q2_K_XL is 3.4 GB.
What context length does Ministral 3 8B 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 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Ministral 3 8B Instruct 2512 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/Ministral-3-8B-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 8B 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 quantization requires about 4.3 GB of VRAM at 8k context, fitting within an 8 GB budget.
Does the GGUF file include the vision encoder?
No, the GGUF files contain only the text model; the vision tower is not included.
What license applies to this model?
The model is licensed under Apache‑2.0, allowing commercial and non‑commercial use and modification.