mistral.rs
PulseAugur coverage of mistral.rs — every cluster mentioning mistral.rs across labs, papers, and developer communities, ranked by signal.
- 2026-06-18 product_launch mistral.rs released version 0.8.10 with support for OpenAI-compatible Agent Skills. source
- 2026-06-04 product_launch The mistral.rs project released support for the Gemma 4 12B model, adding multimodal and agentic capabilities. source
- 2026-06-01 product_launch Mistral.rs released version 0.8.2, featuring significant CUDA inference speed improvements. source
-
mistral.rs v0.9.0 achieves 1.8x faster CPU decode speeds than llama.cpp
The mistral.rs project has released version 0.9.0, demonstrating significant performance improvements in CPU decoding for large language models. Benchmarks show that mistral.rs can be up to 1.8 times faster than llama.c…
-
mistral.rs adds OpenAI-compatible agent skills for local models
The mistral.rs project has released version 0.8.10, introducing support for OpenAI-compatible Agent Skills via a /v1/skills endpoint. This new feature allows local open-source models to execute domain instructions and s…
-
mistral.rs adds Gemma 4 12B multimodal and agentic support
The mistral.rs project has added support for Google's Gemma 4 12B model, enabling multimodal capabilities including audio, image, and video processing. This integration allows developers to build agentic applications wi…
-
Mistral.rs boosts CUDA inference speed; non-CUDA status debated
The mistral.rs project has released version 0.8.2, significantly improving CUDA inference speeds by up to 2.8 times compared to llama.cpp on various NVIDIA GPUs. This update focuses on optimizing throughput for models l…