Ministral 3 14B Base 2512 needs about 10.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.2 GB (Q2_K) to 14.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral 3 14B Base 2512 – 13.5B language model with vision
Ministral 3 14B Base 2512 is a 13.5B parameter model with a 0.4B vision encoder. It supports a 256k context window and is designed for edge deployment. The base version is not fine‑tuned for instruction or reasoning tasks.
Good at
- Vision analysis
- Multilingual text generation
- Large context handling
Limits
- No instruction fine‑tuning
- Requires 32GB VRAM in BF16 or less than 24GB RAM/VRAM when quantized
- Apache‑2.0 license
Best for
- Custom chat agents on local hardware
- Fine‑tuning for specialized tasks
- Private AI deployments
Who it’s for. Developers and researchers building local AI solutions that need both language and vision capabilities within constrained hardware. The model is ideal for custom post‑training workflows and edge deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_S | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_M | 6.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_L | 7.2 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_S | 7.8 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_M | 8.2 GB | 10.1 GB | Too big | Get file → | |
| Q5_K_S | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_M | 9.6 GB | 11.5 GB | Too big | Get file → | |
| Q6_K | 11.1 GB | 12.9 GB | Too big | Get file → | |
| Q8_0 | 14.4 GB | 16.2 GB | Too big | Get file → |
For 8GB VRAM use Q4_K_S (7.83 GB file, ~9.7 GB memory at 8k context). For 16GB VRAM use Q5_K_M (9.62 GB file, ~11.5 GB memory). For 32GB VRAM use Q8_0 (14.36 GB file, ~16.2 GB memory).
What GPU do you need for Ministral 3 14B 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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q3_K_S (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.6 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.1 GB file, about 12.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.4 GB file, about 16.2 GB in use).
Which Ministral 3 14B Base 2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 14B Base 2512: it balances file size and quality well. Here it is a 8.2 GB file.
The Q8_0 file is 14.4 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 5.2 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 Base 2512
How much VRAM does Ministral 3 14B Base 2512 need?
About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.2 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 14B Base 2512 on an 8 GB GPU?
Yes, with Q3_K_S: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 14B Base 2512 GGUF?
It depends on the quant: Q2_K is 5.2 GB, Q3_K_S is 6.1 GB, Q3_K_M is 6.7 GB, Q3_K_L is 7.2 GB, IQ4_XS is 7.5 GB, Q4_K_S is 7.8 GB and 5 more.
What context length does Ministral 3 14B 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Ministral 3 14B Base 2512 GGUF?
The files are on Hugging Face in the mradermacher/Ministral-3-14B-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 14B 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 8 GB VRAM?
Yes, using the Q4_K_S quantized file which requires about 9.7 GB of memory at 8k context.
Does this model support vision tasks?
Yes, it includes a 0.4B vision encoder for image analysis.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.