AI-ML
Ollama v0.16.3
RESUMEN
What's Changed New `ollama launch cline` added for the Cline CLI `ollama launch ` will now always show the model picker Added Gemma 3, Llama and Qwen 3 architectures to MLX runner New Contributors @hellosaumil made their first contribution in
Descripción Detallada
What's Changed New `ollama launch cline` added for the Cline CLI `ollama launch ` will now always show the model picker Added Gemma 3, Llama and Qwen 3 architectures to MLX runner New Contributors @hellosaumil made their first contribution in Full Changelog:
Actualización de Ollama v0.16.3 con nuevas funciones y arquitecturas.
- Se agregó `ollama launch cline` para la CLI de Cline.
- `ollama launch <integration>` ahora siempre mostrará el selector de modelos.
- Se añadieron las arquitecturas Gemma 3, Llama y Qwen 3 al runner MLX.
A quién le importa
Todos los que usan Ollama y la CLI de Cline.
Generado por IA · puede contener errores
Releases Relacionados
AI-ML
Ollama v0.32.5
## What's Changed * Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.4...v0.32.5
AI-ML
Ollama v0.32.4
## What's Changed - Support Laguna on Apple GPUs via the MLX engine - Quantize draft-model output heads at the requested type when creating speculative-decoding drafts. - Fixed Qwen3 MoE decoding for differently-quantized experts, plus faster packed gate/up projection (~4–9% on M5 Max). **Full
AI-ML