Ministral 3 8B reasoning model published in GGUF format
Mistral AI published a GGUF quantized variant of the Ministral-3-8B reasoning model on Hugging Face under Apache-2.0. Tagged 'conversational', this GGUF variant is designed for local inference via llama.cpp and compatible runners.
PUBLISHED2025-10-31
OBSERVED2026-08-11
AGE9mo
SOURCES1
- Model architecture: mistral3 (reasoning variant)
- Format: GGUF (quantized)
- License: Apache-2.0
- Tags: conversational, region:us
- Languages: en, fr, es, de, it, pt, nl, zh, ja, ko, ar
- Base model: mistralai/Ministral-3-8B-Reasoning-2512 (quantized)
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.