Ministral-3-14B-Reasoning-2512 needs about 10.5 GB of memory at Q4_K_M (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 0.0 GB to 27.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral-3-14B-Reasoning-2512: 13.5B parameter LLM with reasoning and tools support
Ministral-3-14B-Reasoning-2512 is a 13.5B parameter language model built on the Mistral 3 architecture. It supports reasoning and tool usage, and is trained on a 262144 token context window. The model is released under the Apache 2.0 license.
Good at
- Reasoning
- Tool usage
- Large context support
Limits
- 262144 token context limit
- Requires 24GB+ RAM/VRAM when unquantized
- No explicit vision support in this variant
Best for
- Custom fine‑tuning
- Private AI deployments
- Local agentic applications
Who it’s for. Developers and researchers who need a large, reasoning‑capable LLM that can be deployed locally or fine‑tuned for specific tasks. The model is suitable for private AI deployments where hardware constraints are a concern.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 3.9 GB | 5.7 GB | Fits | Get file → | |
| IQ1_M | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ2_XXS | 4.5 GB | 6.3 GB | Fits | Get file → | |
| IQ2_XS | 4.8 GB | 6.7 GB | Fits | Get file → | |
| IQ2_S | 5.0 GB | 6.8 GB | Fits | Get file → | |
| Q2_K_S | 5.2 GB | 7.0 GB | Fits | Get file → | |
| IQ2_M | 5.2 GB | 7.0 GB | Fits | Get file → | |
| Q2_K_M | 5.3 GB | 7.2 GB | Fits | Get file → | |
| IQ3_XXS | 6.0 GB | 7.8 GB | Tight | Get file → | |
| IQ3_XS | 6.1 GB | 8.0 GB | Tight | Get file → | |
| Q3_K_S | 6.7 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_M | 6.9 GB | 8.7 GB | Too big | Get file → | |
| IQ4_XS | 7.6 GB | 9.4 GB | Too big | Get file → | |
| IQ4_NL | 7.6 GB | 9.5 GB | Too big | Get file → | |
| Q4_K_S | 8.1 GB | 9.9 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 10.1 GB | Too big | Get file → | |
| Q4_1 | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 8.7 GB | 10.5 GB | Too big | Get file → | |
| Q5_0 | 9.8 GB | 11.6 GB | Too big | Get file → | |
| Q5_K_M | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q5_1 | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q6_K_M | 11.4 GB | 13.3 GB | Too big | Get file → | |
| Q8_0 | 14.4 GB | 16.2 GB | Too big | Get file → | |
| F16 | 19.7 GB | 21.6 GB | Too big | Get file → | |
| BF16 | 27.0 GB | 28.9 GB | Too big | Get file → |
For 8GB VRAM use Q3_K_M (file size 6.9GB, estimated 8.7GB memory at 8k context). For 12GB VRAM use Q4_K_M (8.66GB, 10.5GB memory). For 24GB VRAM use Q5_K_M (10.06GB, 11.9GB memory). Estimates are approximate.
What GPU do you need for Ministral-3-14B-Reasoning-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: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_S (3.9 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (6.1 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_M (11.4 GB file, about 13.3 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (19.7 GB file, about 21.6 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (27.0 GB file, about 28.9 GB in use).
Which Ministral-3-14B-Reasoning-2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral-3-14B-Reasoning-2512: it balances file size and quality well. Here it is a 8.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ministral-3-14B-Reasoning-2512
How much VRAM does Ministral-3-14B-Reasoning-2512 need?
About 10.5 GB at Q4_K_M with an 8K context window. That is the 8.7 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-Reasoning-2512 on an 8 GB GPU?
Yes, with IQ3_XS: the 6.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral-3-14B-Reasoning-2512 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.9 GB, IQ1_M is 4.3 GB, IQ2_XXS is 4.5 GB, IQ2_XS is 4.8 GB, IQ2_S is 5.0 GB and 21 more.
What context length does Ministral-3-14B-Reasoning-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-Reasoning-2512 GGUF?
The files are on Hugging Face in the Mungert/Ministral-3-14B-Reasoning-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-Reasoning-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?
Use the Q3_K_M quantization; it requires about 8.7GB of memory at 8k context, which is close to 8GB VRAM but may need swapping.
Does this model support vision?
The base model includes a vision encoder, but this reasoning variant focuses on text reasoning and tool usage.
What license does it use?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.