# Ollama 0.35.1-rc0 adds ten web searches per response

> The open‑source Ollama model server now lets each reply include up to ten web lookups, and updates its MLX and llama.cpp libraries.

Oossa · 2026-09-29 · https://oossa.com/en/ollama-0-35-1-rc0-adds-ten-web-searches-per-response

Ollama released version 0.35.1‑rc0 on Sep 29, 2026. The build lets a model run up to ten web searches while generating a single answer. It also bumps the MLX library and the llama.cpp engine to newer commits. The change adds an option to declare a model’s explicit capabilities. These tweaks aim to improve answer accuracy and keep the software current.

## The facts

- ten web searches per response – feature added by Parth Sareen
- MLX and llama.cpp libraries updated to newer commits

## Why it matters

More web lookups let Ollama produce fresher, fact‑based answers without leaving the local server.

## Sources & references

1. [ollama/ollama v0.35.1](https://github.com/ollama/ollama/releases/tag/v0.35.1-rc0) – Ollama, 2026-09-29

Last updated: 2026-09-29