AI-ML
Ollama v0.19.0
RESUMEN
Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon is now built on top of Apple’s machine learning framework, ML
Descripción Detallada
Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon is now built on top of Apple’s machine learning framework, MLX, to take advantage of its unified memory architecture. Read more: What's Changed Ollama's app will now no longer incorrectly show "model is out of date" `ollama launch pi` now includes web search plugin that uses Ollama's web search Improved KV cache hit rate when using the Anthropic-compatible API Fixed tool call parsing issue with Qwen3.5 where tool calls would be output in thinking MLX runner will now create periodic snapshots during prompt processing Fixed KV cache snapshot memory leak in MLX runner Fixed issue where flash attention would be incorrectly enabled for `grok` models Fixed `qwen3-next:80b` not loading in Ollama New Contributors * @amatas made their first contribution in Full Changelog:
Ollama v0.19.0 mejora la integración con MLX en Apple Silicon y corrige varios errores.
- Ollama ya no muestra incorrectamente 'modelo desactualizado'.
- El comando `ollama launch pi` ahora incluye un plugin de búsqueda web.
- Mejorada la tasa de aciertos de la caché KV con la API compatible con Anthropic.
- Se corrigieron varios errores relacionados con la carga de modelos y fugas de memoria.
A quién le importa
Todos los que usan Ollama en Apple Silicon.
Generado por IA · puede contener errores
Releases Relacionados
AI-ML
Ollama v0.30.10
## What's Changed * models: add Cohere2MoE model by @jmorganca in https://github.com/ollama/ollama/pull/16670 * llama: update llama.cpp to b9672 by @pdevine in https://github.com/ollama/ollama/pull/16775 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.9...v0.30.10-rc0
AI-ML
Ollama v0.30.9
## What's Changed * Support for Cohere2Moe architecture * Fixed LFM2 parser/render for cases where thinking was not emitted * Fixed issue where `ollama launch claude` and other coding agent or assistant use cases would only output one token * Ollama will now return an error if a single message i