Ministral 3 8B Instruct 2512 needs about 10.7 GB of memory at Q8_0 (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Ministral 3 8B Instruct 2512 – 8.49B parameter LLM with vision, 256k context, Apache 2.0
Ministral 3 8B Instruct 2512 is an 8.49B parameter model with a 256k token context window. It includes a 0.4B vision encoder and supports multilingual instruction following. The model is optimized for edge deployment and runs locally with a small VRAM footprint when quantized.
Good at
- Vision‑enabled instruction following
- Multilingual chat
- Agentic function calling
Limits
- Requires ~10.7 GB VRAM at 8k context (Q8_0)
- Large context window may need additional RAM
- Only Q8_0 quantization provided
Best for
- Embedded chat assistants
- Image description in local apps
- Fine‑tuning for specialized agents
Who it’s for. Developers building local AI assistants on edge hardware. Researchers needing a small, vision‑capable model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → |
The only available quantization is Q8_0, with a file size of 9.03 GB and an estimated memory usage of 10.7 GB at 8k context. For systems with 12 GB VRAM, Q8_0 is suitable. No other quantizations are listed.
What GPU do you need for Ministral 3 8B 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 Q8_0 (9.0 GB file, about 10.7 GB in use).
Which Ministral 3 8B Instruct 2512 quant should you choose?
Q8_0 (9.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Ministral 3 8B Instruct 2512
How much VRAM does Ministral 3 8B Instruct 2512 need?
About 10.7 GB at Q8_0 with an 8K context window. That is the 9.0 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ministral 3 8B Instruct 2512 GGUF?
It depends on the quant: Q8_0 is 9.0 GB.
What context length does Ministral 3 8B 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 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Ministral 3 8B Instruct 2512 GGUF?
The files are on Hugging Face in the ggml-org/Ministral-3-8B-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 8B 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?
No, the Q8_0 quantization requires approximately 10.7 GB VRAM at 8k context.
Does it support vision?
Yes, it includes a 0.4B vision encoder for image analysis.
Is it licensed for commercial use?
Yes, it is released under the Apache 2.0 license, allowing commercial use.