Mistral-Heretica-12B
mrcuddle · Published release · Heretic · GGUF / Transformers
Model source
Published by mrcuddle on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.
Declared base model
NeverSleep/Lumimaid-v0.2-12B ↗
mistralai/Mistral-Nemo-Instruct-2407 ↗
MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy ↗
Hardware and context
Estimated at 7.9 GB VRAM for 12B parameters with 4-bit weights, including 15% weight overhead and 1 GB of baseline headroom. KV cache, context length, multimodal components and concurrency increase actual memory usage.The parameter count was parsed from the model name and has not been independently verified.
Context length: Not stated in public metadata. Please consult the model card.
Download sources and quantized variants
4 repositories| HUGGING FACE REPOSITORY | Format | 30-day downloads | Declared license |
|---|---|---|---|
| AnkitAI/Mistral-Heretica-12B-GGUF ↗ | GGUF | 6.8K | other |
| mradermacher/Mistral-Heretica-12B-i1-GGUF ↗ | GGUF | 835 | Not stated |
| mradermacher/Mistral-Heretica-12B-GGUF ↗ | GGUF | 424 | Not stated |
| mrcuddle/Mistral-Heretica-12B ↗ | Transformers | 88 | Not stated |