Ministral 3 3B Instruct 2512 Heresy Unfiltered needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 2.1 GB (Q4_K_M) to 6.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Ministral 3 3B Instruct 2512 Heresy Unfiltered – a 3.43B parameter, unfiltered instruction model
Ministral 3 3B Instruct 2512 Heresy Unfiltered is a 3.43B parameter model fine‑tuned for instruction tasks. It supports a 256k context window and is available in several GGUF quantizations. The model is released under Apache 2.0 and can run on edge hardware with modest VRAM.
Good at
- Instruction following
- Unfiltered narrative generation
- Low‑resource deployment
Limits
- No vision support in this quantization
- Requires 8k context for memory estimates
- Unfiltered content may violate safety guidelines
Best for
- Chatbots on low‑VRAM GPUs
- Real‑time role‑play engines
- Edge inference on mobile devices
Who it’s for. Developers needing a small, instruction‑capable LLM for edge or low‑resource environments. The model is suitable for applications that can tolerate unfiltered content and require a large context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 5.0 GB | Fits | Get file → | |
| — | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8GB VRAM, use Q4_K_M (2.15GB file, ~3.5GB RAM at 8k context). For 12GB VRAM, Q5_K_M (2.47GB file, ~3.8GB RAM). For 16GB VRAM, Q6_K (2.82GB file, ~4.2GB RAM). All estimates are approximate.
What GPU do you need for Ministral 3 3B Instruct 2512 Heresy Unfiltered?
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 Q5_K_M (2.5 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.9 GB file, about 8.2 GB in use).
Which Ministral 3 3B Instruct 2512 Heresy Unfiltered quant should you choose?
Q4_K_M is the usual starting point for Ministral 3 3B Instruct 2512 Heresy Unfiltered: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Ministral 3 3B Instruct 2512 Heresy Unfiltered
How much VRAM does Ministral 3 3B Instruct 2512 Heresy Unfiltered need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 3B Instruct 2512 Heresy Unfiltered on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ministral 3 3B Instruct 2512 Heresy Unfiltered GGUF?
It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.5 GB, Q6_K is 2.8 GB, Q8_0 is 3.7 GB, file is 6.9 GB.
What context length does Ministral 3 3B Instruct 2512 Heresy Unfiltered support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Ministral 3 3B Instruct 2512 Heresy Unfiltered GGUF?
The files are on Hugging Face in the Abiray/Ministral-3-3B-Instruct-2512-Heresy-Unfiltered-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 3B Instruct 2512 Heresy Unfiltered 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, the Q4_K_M quantization requires about 3.5GB of RAM at 8k context, fitting within 8GB VRAM.
Does this model support vision?
No, the provided GGUF files do not include vision capabilities.
What license does it use?
The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.