model

Ministral 8B

modelactiveprovisionalministral-8b-ffe12c86·1 events·first seen 15d ago

Aliases: Ministral 8B

Co-occurring entities

Mistral AI Gemma 2 9B Llama 3.2 Sliding Window Attention Mistral Large 2 Gemma 2 La Plateforme Mistral 7B Ministral 3B vLLM Llama-3.1-8B

More like this (12)

Ministral 3B LLaDA-8B EvoCUA-8B LLaDA-8B-Base Magistral Small Codestral 22B Mixtral 8x22B Mathstral 7B Fara-7B LLaDA-1.5-8B Llama-Krikri-8B Mistral 7B

Recent events (1)

7Mistral Ai News·15d ago·source ↗

Mistral AI Releases Ministral 3B and 8B Edge Models

Mistral AI has introduced two new small language models, Ministral 3B and Ministral 8B, targeting on-device and edge computing use cases. Both models support up to 128k context length and claim state-of-the-art performance in the sub-10B parameter category, outperforming comparable models from Google and Meta on internal benchmarks. Ministral 8B features an interleaved sliding-window attention mechanism for memory-efficient inference and is priced at $0.1/M tokens via API, while Ministral 3B is priced at $0.04/M tokens. Weights for Ministral 8B Instruct are available for research use, with commercial licensing available on request.

Long Context Evolution Frontier Model Releases Mistral AI Gemma 2 9B Ministral 8B +12 more