Ollama Release Notes

Name: Ollama
Brand: Ollama

Follow Ollama to add their release notes to your feed!

26 release notes curated from 1 source by the Releasebot Team. Last updated: Jun 8, 2026

Get this feed:

Jun 8, 2026
Date parsed from source:
Jun 8, 2026

First seen by Releasebot:
Jun 8, 2026

Modified by Releasebot:
Jun 9, 2026
Ollama

v0.30.7

Ollama launches Hermes Desktop support, bringing a native desktop interface for the Hermes agent. The update also adds Windows config path support, aligns the OpenAI-compatible API model list with available tags, and refreshes documentation and Zod schema examples.
Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps.

ollama launch hermes-desktop

What's Changed

Hermes Desktop is now available via ollama launch hermes-desktop with native Windows configuration path support

OpenAI-compatible API models list now aligns with available model tags

Added documentation describing the llama.cpp update process

Updated Zod schema examples to use the native toJSONSchema helper

Full Changelog: v0.30.6...v0.30.7
Original source
Jun 6, 2026
Date parsed from source:
Jun 6, 2026

First seen by Releasebot:
Jun 7, 2026
Ollama

v0.30.7-rc1

Ollama aligns the OpenAI models list with tags.

openai: align models list with tags (#16556)
Original source
All of your release notes in one feed

Join Releasebot and get updates from Ollama and hundreds of other software products.

Create account
Get updates with:
Jun 7, 2026
Date parsed from source:
Jun 7, 2026

First seen by Releasebot:
Jun 7, 2026
Ollama

v0.30.4

Ollama releases Nemotron-3-Ultra and improves performance and reliability across Apple Silicon, Windows, Codex, and Pi workflows, with updated llama.cpp backend support and better handling for MLX-based models and package migration.

New models

Nemotron-3-Ultra: NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

What's Changed

Fixed multimodal models not using GPU on the llama.cpp backend can now use Metal GPU offload on Apple Silicon, improving multimodal performance on supported Macs.

ollama create --experimental now respects REQUIRES in Modelfiles for MLX-based models.

ollama launch codex now cleans up old conflicting Codex profile config before launching.

ollama launch pi now migrates users from the legacy Pi package to the official package and preserves the correct npm install prefix.

Pi web search setup now updates only when a newer package is available.

Windows cleanup now terminates the llama.cpp backend more reliably.

Updated the llama.cpp backend.

Known Issues

gemma4:12b crashes with floating point exception

Full Changelog: v0.30.3...v0.30.4
Original source
Jun 6, 2026
Date parsed from source:
Jun 6, 2026

First seen by Releasebot:
Jun 6, 2026
Ollama

v0.30.7-rc0

Ollama launches native Windows Hermes config path support.

launch: use native Windows Hermes config path (#16558)
Original source
Jun 7, 2026
Date parsed from source:
Jun 7, 2026

First seen by Releasebot:
Jun 5, 2026

Modified by Releasebot:
Jun 7, 2026
Ollama

v0.30.6

Ollama adds Gemma 4 QAT weights and improves Apple Silicon quantization with MLX embedding layer updates.
New models

Gemma 4 QAT weights: the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the tags ending in -qat:

gemma4:e2b-it-qat

gemma4:e4b-it-qat

gemma4:12b-it-qat

gemma4:26b-a4b-it-qat

gemma4:31b-it-qat

What's Changed

ollama launch omp now integrates with Oh My Pi, an AI coding agent with IDE integration

MLX embedding layers now use NVFP4 global scale for improved quantization on Apple Silicon

Full Changelog: v0.30.5...v0.30.6
Original source
Jun 5, 2026
Date parsed from source:
Jun 5, 2026

First seen by Releasebot:
Jun 5, 2026
Ollama

v0.30.6-rc0

Ollama launches oh-my-pi.

launch: oh-my-pi (#16410)
Original source
Jun 7, 2026
Date parsed from source:
Jun 7, 2026

First seen by Releasebot:
Jun 5, 2026

Modified by Releasebot:
Jun 7, 2026
Ollama

v0.30.5

Ollama fixes a gemma4:12b crash, improves launch support for Hermes Desktop and Windows installs, and adds Cline CLI docs.

What's Changed

Fixed the gemma4:12b floating point exception crash on x86, CUDA, Linux, and Windows systems.

ollama launch hermes-desktop now launches Hermes Desktop and can skip rebuilding when a packaged desktop app is already installed.

ollama launch hermes now supports native Windows installs through the Hermes PowerShell installer.

Added Cline CLI integration docs.

Full Changelog: v0.30.4...v0.30.5
Original source
Jun 4, 2026
Date parsed from source:
Jun 4, 2026

First seen by Releasebot:
Jun 5, 2026
Ollama

v0.30.5-rc0: llama.cpp version update (#16511)

Ollama bumps llama.cpp to b9509, fixing Gemma 4 12B multimodal crashes across x86, CUDA, Linux, and Windows.

Bump llama.cpp to b9509, which includes the upstream Gemma 4 12B multimodal projector fixes for the n_head=0 divide-by-zero crash seen on x86/CUDA/Linux/Windows.

Fixes #16479

Fixes #16489

Fixes #16491

Fixes #16492

Fixes #16495
Original source
Jun 4, 2026
Date parsed from source:
Jun 4, 2026

First seen by Releasebot:
Jun 4, 2026
Ollama

v0.30.4

Ollama ships a small update with a llama.cpp version bump and a Windows cleanup fix for llama-server.

What's Changed

llama.cpp version update by @dhiltgen in #16463

Kill llama-server during Windows cleanup by @dhiltgen in #16458

Known Issues

gemma4:12b crash with floating point exception

Full Changelog: v0.30.3...v0.30.4
Original source
Jun 3, 2026
Date parsed from source:
Jun 3, 2026

First seen by Releasebot:
Jun 4, 2026
Ollama

v0.30.4-rc1: llama-server: fix gemma4 patch wiring (#16477)

Ollama fixes the clip.cpp:4399 unknown projector type crash.

This will fix the "clip.cpp:4399: Unknown projector type" crash.
Original source
Jun 3, 2026
Date parsed from source:
Jun 3, 2026

First seen by Releasebot:
Jun 4, 2026
Ollama

v0.30.4-rc0: Kill llama-server during Windows cleanup (#16458)

Ollama fixes Windows cleanup so llama-server.exe no longer stays running after ollama.exe is killed directly.

Windows installer and app cleanup could leave llama-server.exe running when ollama.exe was killed directly, so cleanup now includes llama-server.exe and taskkill /T.
Original source
Jun 7, 2026
Date parsed from source:
Jun 7, 2026

First seen by Releasebot:
Jun 4, 2026

Modified by Releasebot:
Jun 7, 2026
Ollama

v0.30.3

Ollama adds gemma4:12b support for high-performance multimodal AI that runs directly on laptops.

New models

Gemma 4 12B: high-performance multimodal intelligence that runs directly on laptops, combining efficiency with advanced reasoning.

What's Changed

Added support for gemma4:12b.

Full Changelog: v0.30.2...v0.30.3
Original source
Jun 3, 2026
Date parsed from source:
Jun 3, 2026

First seen by Releasebot:
Jun 3, 2026
Ollama

v0.30.2

Ollama ships launch and model-serving improvements, including Cline CLI auto-install, Qwen code integration, better local model limits, stronger troubleshooting logs, and fixes for markdown URL handling, server stalls, and llama.cpp compatibility.
What's Changed

feat(launch): show and auto-install Cline CLI by @hoyyeva in #16402

log template details to aid troubleshooting by @dhiltgen in #16403

cmd/launch: add Qwen code integration by @hoyyeva in #15900

launch: fix opencode local model limits by @dhiltgen in #16425

llm: include cached prompt tokens in llama-server counts by @dhiltgen in #16428

Harden app markdown URL handling by @dhiltgen in #16380

discover: allow Radeon 8060S iGPU by default by @dhiltgen in #16429

llm: detect llama-server load stalls from output by @dhiltgen in #16427

More harden app markdown URL handling by @dhiltgen in #16436

llama.cpp version update by @dhiltgen in #16426

launch: isolate Codex launch configuration by @ParthSareen in #16437

llama: add laguna (poolside) arch via a llama.cpp patch under llama/c… by @dhiltgen in #16396

docs: configure hermes desktop app by @BruceMacD in #16440

llm: ignore llama-server SSE ping comments by @dhiltgen in #16443

fix laguna patch build breakage by @dhiltgen in #16445

Full Changelog: v0.30.0...v0.30.2-rc0
Original source
Jun 2, 2026
Date parsed from source:
Jun 2, 2026

First seen by Releasebot:
Jun 3, 2026
Ollama

v0.30.2-rc0: fix laguna patch build breakage (#16445)

Ollama fixes kernel template instantiation so library symbols are exported correctly.

Follow up to #16396

Fix kernel template instantiation so the symbols are exported in the library.
Original source
Jun 2, 2026
Date parsed from source:
Jun 2, 2026

First seen by Releasebot:
Jun 3, 2026
Ollama

v0.30.1: llm: ignore llama-server SSE ping comments (#16443)

Ollama fixes SSE streaming by skipping idle comment frames in completion and chat requests.

llama.cpp b9478 added a default 30s SSE ping that emits colon-only comment frames (":\n\n") while streamed requests are idle; Ollama treated non-data SSE lines as JSON, so skip SSE comments in completion and chat streams.
Original source

Curated by the Releasebot team

Releasebot is an aggregator of official release notes from hundreds of software vendors and thousands of sources.

Our editorial process involves the manual review and audit of release notes procured with the help of automated systems.

About us Our methodology

Ollama Release Notes

v0.30.7

What's Changed

v0.30.7-rc1

v0.30.4

New models

What's Changed

Known Issues

v0.30.7-rc0

v0.30.6

New models

What's Changed

v0.30.6-rc0

v0.30.5

What's Changed

v0.30.5-rc0: llama.cpp version update (#16511)

v0.30.4

What's Changed

Known Issues

v0.30.4-rc1: llama-server: fix gemma4 patch wiring (#16477)

v0.30.4-rc0: Kill llama-server during Windows cleanup (#16458)

v0.30.3

New models

What's Changed

v0.30.2

What's Changed

v0.30.2-rc0: fix laguna patch build breakage (#16445)

v0.30.1: llm: ignore llama-server SSE ping comments (#16443)

Curated by the Releasebot team

Similar to Ollama with recent updates: