Ministral 3 14B Instruct 2512 BF16 needs about 10.7 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 18 quants, from 5.1 GB (Q2_K_S) to 27.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Ministral 3 14B Instruct 2512 BF16 – a 13.5B multimodal LLM with 256k context
Ministral 3 14B Instruct 2512 BF16 is a 13.5B language model with a 0.4B vision encoder. It supports a 256k context window and is trained for instruction tasks. The model is edge‑optimized and can run locally on a wide range of hardware.
Good at
- Large context handling
- Instruction‑driven chat
- Multimodal vision analysis
Limits
- No vision support in quantized versions
- Requires 32 GB VRAM in BF16
- Apache 2.0 license limits commercial use to open‑source terms
Best for
- Private AI assistants
- Local agentic workflows
- Fine‑tuning on edge devices
Who it’s for. Developers and researchers needing a powerful yet deployable multimodal LLM. The model is suitable for private or custom chat deployments in constrained environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_S | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q2_K | 5.6 GB | 7.5 GB | Tight | Get file → | |
| Q3_K_S | 6.5 GB | 8.4 GB | Too big | Get file → | |
| Q2_K_L | 6.9 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_M | 7.7 GB | 9.6 GB | Too big | Get file → | |
| Q4_K_S | 8.2 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_L | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 10.7 GB | Too big | Get file → | |
| Q5_K_S | 9.3 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_XL | 10.0 GB | 11.8 GB | Too big | Get file → | |
| Q3_K_XL | 10.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 10.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_XL | 10.8 GB | 12.7 GB | Too big | Get file → | |
| Q6_K | 11.1 GB | 12.9 GB | Too big | Get file → | |
| Q6_K_L | 12.3 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 14.4 GB | 16.2 GB | Too big | Get file → | |
| Q8_0 | 19.2 GB | 21.0 GB | Too big | Get file → | |
| F16 | 27.0 GB | 28.9 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K_S (5.14 GB file, ~7 GB memory). For 16 GB VRAM use Q4_K_S (8.16 GB file, ~10 GB memory). For 32 GB VRAM use the BF16 model (27.02 GB file, ~28.9 GB memory). Estimates are approximate.
What GPU do you need for Ministral 3 14B Instruct 2512 BF16?
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 Q2_K (5.6 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (10.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_L (12.3 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.2 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (27.0 GB file, about 28.9 GB in use).
Which Ministral 3 14B Instruct 2512 BF16 quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 14B Instruct 2512 BF16: it balances file size and quality well. Here it is a 8.8 GB file.
The Q8_0 file is 14.4 GB, about 1.6 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_S at 5.1 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 Instruct 2512 BF16
How much VRAM does Ministral 3 14B Instruct 2512 BF16 need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 8.8 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 Instruct 2512 BF16 on an 8 GB GPU?
Yes, with Q2_K: the 5.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 14B Instruct 2512 BF16 GGUF?
It depends on the quant: Q2_K_S is 5.1 GB, Q2_K is 5.6 GB, Q3_K_S is 6.5 GB, Q2_K_L is 6.9 GB, Q3_K_M is 7.7 GB, Q4_K_S is 8.2 GB and 12 more.
What context length does Ministral 3 14B Instruct 2512 BF16 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 Instruct 2512 BF16 GGUF?
The files are on Hugging Face in the EnlistedGhost/Ministral-3-14B-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 14B Instruct 2512 BF16 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 Q2_K_S quantized file which is 5.14 GB and requires about 7 GB of VRAM at 8k context.
Does the model support vision tasks after quantization?
The quantized GGUF files retain the vision encoder, so vision tasks are supported in all quantized versions.
What license applies to this model?
The model is licensed under Apache 2.0, allowing commercial and non‑commercial use with attribution.