Ministral-3-8B-Reasoning-2512 needs about 7.2 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 17.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Ministral‑3‑8B‑Reasoning‑2512 – a reasoning‑optimized 8.5B model with vision
Ministral‑3‑8B‑Reasoning‑2512 is a 8.5B parameter model trained for reasoning tasks. It includes an 8.4B language core and a 0.4B vision encoder. The model supports a 262144 token context window and is licensed under Apache‑2.0.
Good at
- Reasoning and math
- Coding and STEM queries
- Vision‑enabled text analysis
Limits
- No vision support in quantized variants
- Large context window requires significant VRAM
- Requires 24GB VRAM in BF16
Best for
- Math problem solving
- Code generation
- Image‑based document analysis
Who it’s for. Developers and researchers needing a reasoning‑focused model that can run locally on edge hardware. The model is suitable for custom fine‑tuning and specialized agentic applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_XS | 3.1 GB | 4.8 GB | Fits | Get file → | |
| IQ2_S | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ2_M | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_XS | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 4.3 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 4.4 GB | 6.1 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 5.1 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 5.3 GB | 7.0 GB | Fits | Get file → | |
| Q4_1 | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.5 GB | 7.2 GB | Fits | Get file → | |
| Q5_0 | 6.2 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.4 GB | 8.0 GB | Too big | Get file → | |
| Q5_1 | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q6_K_M | 7.2 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → | |
| F16 | 12.6 GB | 14.2 GB | Too big | Get file → | |
| BF16 | 17.0 GB | 18.6 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_S (file size 5.14 GB, estimated 6.8 GB memory at 8k context). For 12‑GB VRAM, Q5_K_M (6.41 GB, 8 GB memory) is a good balance. For 24‑GB VRAM, BF16 (12.58 GB, 14.2 GB memory) provides full precision.
What GPU do you need for Ministral-3-8B-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 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.4 GB file, about 8.0 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 F16 (12.6 GB file, about 14.2 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-Reasoning-2512 quant should you choose?
Q4_K_M is the usual starting point for Ministral-3-8B-Reasoning-2512: it balances file size and quality well. Here it is a 5.5 GB file.
The Q8_0 file is 9.0 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 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-3-8B-Reasoning-2512
How much VRAM does Ministral-3-8B-Reasoning-2512 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.5 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-Reasoning-2512 on an 8 GB GPU?
Yes, with Q5_K_M: the 6.4 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-3-8B-Reasoning-2512 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB, Q2_K_S is 3.3 GB, IQ2_M is 3.3 GB and 19 more.
What context length does Ministral-3-8B-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 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Ministral-3-8B-Reasoning-2512 GGUF?
The files are on Hugging Face in the Mungert/Ministral-3-8B-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-3-8B-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 8 GB VRAM?
Yes, using the Q4_K_S quantization which requires about 6.8 GB of VRAM at 8k context.
Does the model support vision tasks?
Yes, it includes a 0.4B vision encoder for image analysis.
What license does it use?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.