PulseAugur
EN
LIVE 09:11:16

Ollama v0.40.14 release improves Claude Code token limits and API handling

By PulseAugur Editorial · [1 sources] ·

Ollama has released version v0.40.14, introducing several key updates. The release ensures that launching Claude Code via Ollama now respects the model's specific output token limit, preventing issues with the default 128k cap. Additionally, cloud web search responses through the `/api/chat` endpoint are now correctly decoded, even for compressed data. The update also modifies OpenAI-compatible endpoints to prevent overriding a model's default sampler settings when temperature or top_p parameters are not explicitly provided by the client. AI

IMPACT Enhances the usability and stability of local LLM deployments, particularly for models like Claude Code.

RANK_REASON Software release for a tool that runs LLMs locally.

Read on Mastodon — sigmoid.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Ollama v0.40.14 release improves Claude Code token limits and API handling

How we ranked this

Signal score
7 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Software release for a tool that runs LLMs locally.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    ⚙️ New Ollama Release! ⚙️ Version: v0.40.14 Release Notes: ## What's Changed * `ollama launch claude` now applies the model's output token limit for Claude Code

    ⚙️ New Ollama Release! ⚙️ Version: v0.40.14 Release Notes: ## What's Changed * `ollama launch claude` now applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap * Cloud web search responses on `/api/chat` are now decoded co…

RELATED ENTITIES

RELATED TOPICS