Faster Gemma 4 on MLX with multi-token prediction
4mo
- Published
- Collected
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.
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Ollama Blog.
More from Ollama Blog
Log in to follow this source
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.
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.
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.
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.