model

Mixtral 8x7B Instruct

modelactiveprovisionalmixtral-8x7b-instruct-c9ed9043·1 events·first seen 15d ago

Aliases: Mixtral 8x7B Instruct

Co-occurring entities

Mistral AI Llama 2 70B Mistral Small 4 MT-Bench Megablocks Sparse Mixture-of-Experts Direct Preference Optimization (DPO)GPT-3.5 BOLD Mixtral 8x7B CoreWeave Scaleway BBQ vLLM

More like this (12)

Mixtral 8x22B Mixtral-8x7B-v0.1 Mixtral 8x7B Mixtral Qwen2-Audio-7B-Instruct Dream-7B-Instruct Mistral 7B Instruct v0.2 Qwen3-30B-A3B-Instruct Qwen2.5-VL-32B-Instruct Moonlight-16B-A3B-Instruct Llama3-8B-Instruct LLaDA-8B

Recent events (1)

9Mistral Ai News·15d ago·source ↗

Mixtral 8x7B: Mistral AI Releases Sparse Mixture-of-Experts Open-Weight Model

Mistral AI has released Mixtral 8x7B, a sparse mixture-of-experts (SMoE) model with 46.7B total parameters but only 12.9B active parameters per token, enabling inference speed and cost equivalent to a 12.9B model. Licensed under Apache 2.0, Mixtral outperforms Llama 2 70B on most benchmarks and matches or exceeds GPT-3.5, with support for 32k context, five European languages, and strong code generation. An instruction-tuned variant (Mixtral 8x7B Instruct) achieves 8.3 on MT-Bench, claimed best among open-source models at release. The model is deployed behind Mistral's mistral-small API endpoint and supported via vLLM with Megablocks CUDA kernels.

Frontier Model Releases Evaluation and Benchmarking Mistral AI Llama 2 70B Mistral Small 4 +15 more