v0.1.804-beta 2.12.0
unslothai/unslothAug 27, 2026 → Aug 25, 20260 days between releases
Generating AI comparison
Analyzing what changed between v0.1.804-beta and 2.12.0. This page updates automatically — usually within a minute.
The Two Releases
Qwen3.8-Flash-Next + GLM-5.3-Flash
Aug 27, 2026· 2 months ago
Added support for Qwen3.8-Flash-Next and GLM-5.3-Flash models, enabling local inference with specific RAM requirements. Includes infinite repeated compaction, chat recovery after disconnects, and fixes for AMD model loading and Linux voice recording.
Full release notes2.12.0
Aug 25, 2026· 2 months ago
A critical security release addressing two vulnerabilities in the MCP endpoint (CVE-2026-45018 and CVE-2026-45019). It introduces significant breaking changes to MCP configuration, removing client-supplied commands and enforcing server-side declaration of stdio servers.
Full release notes