Ministral 3 8B Instruct 2512 needs about 6.8 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.2 GB (Q4_K_M) to 17.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Ministral 3 8B Instruct 2512 – a compact, vision‑enabled instruction model
Ministral 3 8B Instruct 2512 is an 8.4B language model with a 0.4B vision encoder. It supports a 256k context window and is fine‑tuned for instruction tasks. The model runs on edge hardware and fits in 12 GB VRAM in FP8, with lower memory when quantized.
Good at
- Instruction following
- Vision analysis
- Agentic function calling
Limits
- Large context requires 256k tokens
- No native vision support in older quantizations
- Requires Apache‑2.0 license compliance
Best for
- Chat in constrained environments
- Local AI assistant
- Image/document description
Who it’s for. Developers building local or embedded AI assistants that need instruction following and basic vision. The model is suitable for users who want a small footprint with multilingual and agentic capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_M | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → | |
| BF16 | 17.0 GB | 18.6 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (5.2 GB file, ~6.8 GB RAM at 8k context). For 12 GB VRAM use Q5_K_M (6.06 GB file, ~7.7 GB RAM). Higher precision Q8_0 or BF16 requires more than 12 GB VRAM.
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: the best quant that fits is Q5_K_M (6.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.0 GB file, about 18.6 GB in use).
Which Ministral 3 8B Instruct 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 8B Instruct 2512: it balances file size and quality well. Here it is a 5.2 GB file.
The Q8_0 file is 9.0 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 8B Instruct 2512
How much VRAM does Ministral 3 8B Instruct 2512 need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.2 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 8B Instruct 2512 on an 8 GB GPU?
Yes, with Q5_K_M: the 6.1 GB file needs about 7.7 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 GGUF?
It depends on the quant: Q4_K_M is 5.2 GB, Q5_K_M is 6.1 GB, Q8_0 is 9.0 GB, BF16 is 17.0 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 mistralai/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?
Yes, using Q4_K_M quantization the model requires about 6.8 GB of VRAM at 8k context.
Does it support vision tasks?
Yes, the 0.4B vision encoder allows image analysis alongside text.
What license applies?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.