Ollama 0.34.1

UpdateSep 14, 20262 weeks agoUnverifiedAdded Oct 2, 2026

- MLX safetensors ollama create no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. - Improved MLX memory handling on Apple Silicon - Runaway repeat token detection now requires 100 repeat tokens for reduced false positives (e.g.

Topics: LLMs, Governance, Developer tools, Performance

Ollama's release notes

More Ollama releases

Every Ollama release

Date	Release	Type
Sep 172 weeks ago	Ollama 0.34.2 unverified Update	Update
Sep 2211 days ago	Ollama 0.34.3 unverified Update	Update
Sep 249 days ago	Ollama 0.34.4 unverified Update	Update
Sep 285 days ago	Ollama 0.35.0 unverified Update	Update

Also shipped on Sep 14, 2026

Ollama in September 2026

Date	Company	Release	Product	Type
Sep 142 weeks ago	Google Cloud	Metadata for BigQuery Graph is automatically ingested and searchable in Knowledge Catalog Google CloudBigQueryPreview	BigQuery	Preview
Sep 142 weeks ago	Google Cloud	BigQuery supports WHERE clauses inside aggregate function calls in preview Google CloudBigQueryPreview	BigQuery	Preview
Sep 142 weeks ago	Snowflake	Multimodal AI_SUMMARIZE for automatic theme summarization (Public Preview) SnowflakeSnowflake Cortex AIPreview	Snowflake Cortex AI	Preview
Sep 142 weeks ago	Snowflake	Zero-copy support for all table formats in interactive warehouses (General availability) SnowflakeGA	Snowflake	GA
Sep 142 weeks ago	Databricks	Genie visualizations in Slack replies (Public Preview) DatabricksAI/BI and GeniePreview	AI/BI and Genie	Preview
Sep 142 weeks ago	Google Cloud	Metadata for BigQuery Graph is now automatically ingested and searchable in Knowledge Catalog Google CloudDataplex Universal CatalogPreview	Dataplex Universal Catalog	Preview

More Ollama releases

Also shipped on Sep 14, 2026

New releases by email