AI-ML
Ollama v0.21.1
RESUMEN
What's Changed Kimi CLI You can now install and run the Kimi CLI through Ollama. ``` ollama launch kimi --model kimi-k2.6:cloud ``` Kimi CLI with Kimi K2.6 excels at long horizon agentic execution tasks through a multi-agent system. * MLX runner adds logprobs support for comp
Descripción Detallada
What's Changed Kimi CLI You can now install and run the Kimi CLI through Ollama. ``` ollama launch kimi --model kimi-k2.6:cloud ``` Kimi CLI with Kimi K2.6 excels at long horizon agentic execution tasks through a multi-agent system. MLX runner adds logprobs support for compatible models Faster MLX sampling with fused top-P and top-K in a single sort pass, plus repeat penalties applied in the sampler Improved MLX prompt tokenization by moving tokenization into request handler goroutines Better MLX thread safety for array management GLM4 MoE Lite performance improvement with a fused sigmoid router head Fixed model picker showing stale model after switching chats in the macOS app * Fixed structured outputs for Gemma 4 when `think=false` Full Changelog:
Se añade soporte para Kimi CLI y mejoras en MLX.
- Ahora puedes instalar y ejecutar Kimi CLI a través de Ollama.
- MLX runner añade soporte para logprobs en modelos compatibles.
- Mejoras en la velocidad de muestreo de MLX y en la tokenización de prompts.
- Correcciones de errores en el selector de modelos y salidas estructuradas para Gemma 4.
A quién le importa
Todos los que usen Kimi CLI y MLX.
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