Ministral 3 8B Base 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 12 quants, from 3.4 GB (Q2_K) to 17.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Ministral 3 8B Base 2512 – a balanced, vision‑capable LLM for edge deployment
Ministral 3 8B Base 2512 is an 8.49B parameter model with a 262144 token context window. It includes a 0.4B vision encoder and supports dozens of languages. The model is open‑source under Apache 2.0 and is designed for local or embedded use.
Good at
- Vision analysis and image description
- Multilingual text generation
- Large context handling
Limits
- No instruction fine‑tuning built‑in
- Requires 24GB VRAM in BF16 or less than 12GB when quantized
- No vision support in quantized versions that drop the encoder
Best for
- Local chat interfaces in constrained environments
- Embedded AI assistants
- Image/document understanding tasks
Who it’s for. Developers building local or edge AI solutions who need a versatile model with vision and multilingual support. The model is suitable for custom fine‑tuning and post‑training workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 4.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q6_K | 7.0 GB | 8.6 GB | Too big | Get file → | |
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → | |
| F16 | 17.0 GB | 18.6 GB | Too big | Get file → |
For 8GB VRAM use Q4_K_M (5.2GB file, ~6.8GB memory at 8k context). For 12GB VRAM use Q5_K_M (6.06GB file, ~7.7GB memory). For 24GB VRAM use the full F16 (16.99GB file, ~18.6GB memory).
What GPU do you need for Ministral 3 8B Base 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: the best quant that fits is Q3_K_M (4.2 GB file, about 5.9 GB in use).
- 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 F16 (17.0 GB file, about 18.6 GB in use).
Which Ministral 3 8B Base 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 8B Base 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.
If memory is tight, the smallest file is Q2_K at 3.4 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 Base 2512
How much VRAM does Ministral 3 8B Base 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 Base 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 Base 2512 GGUF?
It depends on the quant: Q2_K is 3.4 GB, Q3_K_S is 3.9 GB, Q3_K_M is 4.2 GB, Q3_K_L is 4.6 GB, IQ4_XS is 4.7 GB, Q4_K_S is 5.0 GB and 6 more.
What context length does Ministral 3 8B Base 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 Base 2512 GGUF?
The files are on Hugging Face in the mradermacher/Ministral-3-8B-Base-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 Base 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 8GB VRAM?
Yes, use the Q4_K_M quant which requires about 6.8GB of VRAM at 8k context.
Does the model support vision tasks after quantization?
The quantized files retain the vision encoder, so image analysis remains available.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.