Req-052026-0014

Correo Electronico Solicitud por correo Nuevo

Accelerated Gemma 4 with multi-token prediction

Gemma 4 on Ollama is now 2x faster, with native Multi-Token Prediction (MTP) on macOS via MLX and on Ollama's cloud.

To run the accelerated version of Gemma 4 on Ollama's cloud:

ollama run gemma4:31b-cloud

To use Gemma 4 with Claude, run:

ollama launch claude --model gemma4:31b-cloud

OpenClaw:

ollama launch openclaw --model gemma4:31b-cloud

Hermes Agent:

ollama launch hermes --model gemma4:31b-cloud

Ollama on macOS now supports native MTP support for Gemma 4 via MLX:

ollama run gemma4:31b-coding-mtp-bf16

For more information, please visit Ollama's Gemma 4 model page.

If you have any feedback, please directly reply to this email or join Ollama's Discord channel.

❤️ Ollama

You are receiving this email because you opted-in to receive updates from Ollama
Ollama, 744 High Street, Palo Alto, CA 94301
Unsubscribe

Estado Nuevo

08/05/2026 08:18 Nuevo Creado

Bot 08/05/2026 02:18

Request creado