Reasoning8x7B official

mixtral

by Mistral AI

Mixtral 8x7B — a sparse mixture-of-experts model offering strong quality at high inference efficiency.

arcflare run mixtral

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

Mixtral 8x7B

A sparse mixture-of-experts (MoE) model: it has the quality of a much larger model while only activating a fraction of its parameters per token.

arcflare run mixtral

[ 03 ] // relatedmore →

OpenAI

gpt-oss: OpenAI's open-weight reasoning models. 20B runs in ~16 GB, 120B on one 80 GB card. Apache-2.0, adjustable reasoning effort.

58% of a 24 GB card

#reasoning #tools #moe

Z.ai

GLM-4.5-Air: a 106B MoE with 12B active, hybrid reasoning and strong agent and coding scores, under MIT. Workstation-class.

2.7× a 24 GB card

#moe #agentic #reasoning

DeepSeek

DeepSeek-R1-0528: the updated 671B reasoning model, plus an 8B distill on Qwen3 that runs on a gaming GPU. MIT.

25% of a 24 GB card

#reasoning #math #moe