Releasesby IbisOllama 0.40.4
Update12 days agoUnverifiedAdded Oct 17, 2026
Decision models in the CLI Decision models can now be used directly from the terminal with ollama run , ask yes/no questions, classify text into labels, or score against a rubric: ollama run nimble --ask "Is a refund being requested?" < ticket.txt ## - Kev decision models are now supported by the MLX runner on Apple silicon - ollama launch can now be used...
Topics: LLMs, Vector search, Pricing, Developer tools, Coding agents
More Ollama releases
Every Ollama releaseOllama 0.40.3
- ollama launch claude no longer shows a warning about Claude connectors - ollama launch codex no longer warns about service tiers - Paused background model upgrade for embedding and other request performance,
Ollama 0.40.5
NVIDIA Nemotron 3.5 Super NVIDIA Nemotron 3.5 Super is a vision-language model for coding, reasoning, tool use, and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture-of-experts backbone (12B active per token) with a C-RADIO vision encoder, and supports tool calling, an on/off thinking mode, and context up to 1M tokens.
Ollama 0.40.6
- win: prevent orphaned runners - gguf: add the q2_0 tensor and file types - Launch clef in Ollama's cloud - use identifiers for --ask mode question keys
Ollama 0.40.2
Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp. To make downgrading safe, Ollama keeps the original copy as a backup, so upgraded models are temporarily kept on disk.
Ollama 0.40.1
- server: proxy cloud usage and balance APIs - llama: fix clef head reads past 2GiB on windows - cmd: remove account step from CLI onboarding - manifest: avoid symlinks on Windows - docs: fix 6 dead links in README community integrations list - docs: fix broken download links in app README - mlx: drop carried metal residency patch now that it is upstream
Ollama 0.40.7
- pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B - Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items - Fixed streaming Responses requests where client tool calls (e.g.
Ollama 0.40.8
Recursive Flint Flint brings Recursive's coding model to Ollama. It is designed for the work coding agents do across a repository: understanding unfamiliar code, tracing bugs, implementing features, and adding tests. Reasoning, multi-turn tool use, and a 262K-token context window support longer tasks across files and tool interactions.
Ollama 0.40.9
Speech Ollama can now generate speech with Phonon on Apple Silicon. ollama run plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible /v1/audio/speech endpoint. sh ollama run phonon "Hello from Ollama." d3 decision models d3 brings vLLM Semantic Router's decision models to Ollama.
Also shipped on Oct 12, 2026
Ollama in October 2026Change an incident’s conference bridge without leaving Slack with /pd meeting now Generally Available
Run /pd meeting during an incident, paste the new link, and PagerDuty updates the incident card instantly with a Join meeting button in the channel. Scribe Agent follows along to the new meeting on its own, so you keep the transcript for your post-incident review. Available to customers using the Pa...
New Incident Workflow action: Get Slack Mentions for Incident Participants now Generally Available
This new Incident Workflow action pulls the assignees, acknowledgers, and role holders on an incident and turns them into Slack @mentions. Pair it with Send Slack Message to tag everyone involved without hard-coding names, so the same workflow works across every team and rotation. Available to Pager...
Conference bridge selection in the Slack declare modal now Generally Available
Declare an incident with /pd declare and choose one of your pre-configured PagerDuty conference bridges from a dropdown, or paste a meeting URL if you don't have one set up. The bridge is on the incident from the moment it's declared, so responders can join from Slack in one click. Available to cust...
Incremental data transfers for the BigQuery Data Transfer Service for PostgreSQL and ServiceNow are now...
Incremental data transfers for the BigQuery Data Transfer Service for PostgreSQL and ServiceNow are now generally available (GA).
Support for Budget spend caps to pause your Cloud Run workloads is in General Availability (GA)
Support for Budget spend caps to pause your Cloud Run workloads is in General Availability (GA) .
End-to-end Snowflake Observability is now generally available in Dynatrace
Dynatrace Snowflake Observability is now generally available in the Dynatrace Data Observability app, offering automated telemetry collection and 14 pre-built dashboards for monitoring cost, performance, and data quality.