Model index / Mistral / Mistral-Small-4-119B-2603-heretic
Mistral / MODEL PROFILE

Mistral-Small-4-119B-2603-heretic

darkc0de · Published release · Heretic · GGUF / NVFP4 / Transformers

Model familyMistral
Parameters119B
Estimated Q4 VRAMAbout 69.4 GB
30-day downloads16.9K
Declared licenseNot stated
Source repositories4

Model source

Published by darkc0de 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

mistralai/Mistral-Small-4-119B-2603 ↗

Hardware and context

Estimated at 69.4 GB VRAM for 119B 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 REPOSITORYFormat30-day downloadsDeclared license
Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf ↗GGUF12.1Kapache-2.0
Rioky/Mistral-Small-4-119B-2603-heretic-gguf ↗GGUF4.4Kapache-2.0
GulfCoastAI/Mistral-Small-4-119B-Heretic-NVFP4 ↗NVFP4180apache-2.0
darkc0de/Mistral-Small-4-119B-2603-heretic ↗Transformers139Not stated
Uncensored is a publisher description, not a guarantee of zero refusals, capability, accuracy or safety. This index does not measure refusal rates or performance benchmarks.

More from this family

More Mistral →