v9.14.0 v0.9.5
EricLBuehler/mistral.rsOct 6, 2026 → Oct 19, 202613 days between releases
Generating AI comparison
Analyzing what changed between v9.14.0 and v0.9.5. This page updates automatically — usually within a minute.
The Two Releases
v9.14.0
v9.14.0
Oct 6, 2026· 16 days ago
This release introduces new ANN backends for RaBitQ and Zvec Sparse, alongside native support for ONNX vectors. It includes a significant number of improvements and bug fixes to enhance performance and stability.
Full release notesv0.9.5
v0.9.5
Oct 19, 2026· 3 days ago
This release introduces support for the Qwen3.8-Flash-Next model, updates CUDA compatibility to version 13.4, and makes Metal Paged Attention the default backend. It also includes fixes for tool-call delimiters, GCC 13+ compatibility, and quantization deadlock issues.
Full release notes