Faster Gemma 4 on MLX with multi-token prediction

4mes

Antigüedad

Publicado: 29 jun 2026, 0:00 UTC
Recolectado: 29 oct 2026, 19:02 UTC

Gemma 4 is now significantly faster in Ollama 0.31 on Apple Silicon via multi-token prediction (MTP), powered by MLX. Performance is now up to 90% faster when used with coding agents, as measured using the Aider polyglot benchmark.

Lee el artículo completo en ollama.com

overfeed.news indexa y enlaza. Publicamos un extracto breve; el artículo completo sigue en Ollama Blog.

Más de Ollama Blog

Inicia sesión para seguir esta fuente

Ollama Bloghace 20 días

Speech models in Ollama

Ollama now supports speech models, starting with Phonon from Gradium. Read text aloud in five languages and dozens of voices, streamed as it is generated, over 100 times faster than real time on Apple Silicon.

Ollama Bloghace 25 días

Clef is available on Ollama's cloud

Clef, a 27B multimodal decision model from Cloudflare, is now available on Ollama. Run it locally or on Ollama's cloud.

Ollama Bloghace 28 días

Reflection's Beam is freely available on Ollama for a limited time

Reflection's first open-weight model is now available on Ollama, and free for a limited time only. Beam is designed for software engineering, reasoning, and long-running agentic tasks. Access Beam through Ollama's cloud.

Ollama Blogel mes pasado

Run AI agents safely with Ollama and Fly.io

AI agents can now use Ollama's cloud models safely inside Fly.io's cloud computers.

Más de Ollama Blog

Speech models in Ollama↗

Clef is available on Ollama's cloud↗

Reflection's Beam is freely available on Ollama for a limited time↗

Run AI agents safely with Ollama and Fly.io↗

Speech models in Ollama

Clef is available on Ollama's cloud

Reflection's Beam is freely available on Ollama for a limited time

Run AI agents safely with Ollama and Fly.io