Mistral Heretica 12B needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 7.5 GB (Q4_K_M) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Mistral Heretica 12B – 12B parameter model tuned for uncensored roleplay and creative writing
Mistral Heretica 12B is a 12‑billion parameter model built on the Mistral architecture. It merges Mistral‑Nemo‑Instruct‑2407, Lumimaid‑v0.2‑12B, and absolute‑heresy to deliver uncensored roleplay and creative writing capabilities. The model is available in several GGUF quantizations for llama.cpp and compatible front‑ends.
Good at
- Uncensored roleplay
- Creative writing
- Mistral‑instruct format
Limits
- No vision support
- License is non‑commercial unless verified
- Large context requires 131072 tokens
Best for
- Roleplay sessions
- Creative story generation
- In‑house LLM demos
Who it’s for. Developers and hobbyists who need a large, text‑only model for roleplay or creative writing. The model is suitable for local deployment with llama.cpp, LM Studio, Ollama, or other compatible front‑ends.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → |
For 8 GB RAM/VRAM, use Q4_K_M (7.48 GB file, ~9.3 GB memory at 8 k context). For 12 GB, Q5_K_M or Q6_K are suitable (8.73 GB or 10.06 GB files). For 16 GB+, Q6_K or Q8_0 provide higher quality. Estimates are approximate.
What GPU do you need for Mistral Heretica 12B?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
Which Mistral Heretica 12B quant should you choose?
Q4_K_M is the usual starting point for Mistral Heretica 12B: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.0 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
Source
Frequently asked questions about Mistral Heretica 12B
How much VRAM does Mistral Heretica 12B need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Mistral Heretica 12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral Heretica 12B GGUF?
It depends on the quant: Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB, Q8_0 is 13.0 GB.
What context length does Mistral Heretica 12B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Mistral Heretica 12B GGUF?
The files are on Hugging Face in the AnkitAI/Mistral-Heretica-12B-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 Mistral Heretica 12B use?
Hugging Face lists the license as other. 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 Mistral Heretica 12B on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 9.3 GB of VRAM at 8 k context, so it fits on 8 GB with a small buffer.
Does this model support image input?
No, the model is text‑only and has no vision capabilities.
What license applies to this model?
The model inherits non‑commercial terms from its source models, notably CC‑BY‑NC‑4.0. Use it only for non‑commercial purposes unless verified otherwise.