shipfeedAI news, curated daily

18:18:27 CET
25 AUG18:18:27shipfeed
pull to refreshlast sync
Just in — 8 new
§ topic

ollama

5 stories · 7d·6 sources covering·30 active storylines

Updated Sat, 22 Aug 2026 CEST·5 new storylines this week·live

What this is

Ollama is an open-source tool for running open-weight LLMs locally with one command. shipfeed tracks Ollama releases, new model support, and API and platform updates.

storylines this week30 active

Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc27

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc17

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Thursday, April 2, 2026’s edition
Ollama — Releases
OLLAMA · 1 source

Ollama v0.20.0

Gemma 4 Effective 2B (E2B) ``` ollama run gemma4:e2b ``` Effective 4B (E4B) ``` ollama run gemma4:e4b ``` 26B (Mixture of Experts model with 4B active parameters) ``` ollama run gemma4:26b ``` 31B (Dense) ``` ollama…

via github.com
Saturday, August 22, 2026’s edition
Ollama — Releases
OLLAMA · v0.33.0-rc0

Adds Claude Desktop App integration

What's Changed mlx: fix mac assumptions on linux/windows by @dhiltgen in https://github.com/ollama/ollama/pull/17898 mlx update by @dhiltgen in https://github.com/ollama/ollama/pull/17886 lint fixes by @dhiltgen in…

via github.com
Ollama — Releases
OLLAMA · v0.33.0-rc3

Adds Ollama model selection to Claude Desktop

What's Changed Claude Desktop Turn individual Ollama models on or off for use in Claude, directly from the menu bar Choose from your available Ollama models from within Claude; cloud models appear only when you're…

via github.com
Friday, August 14, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.12

Adds Qwen 3.8 27B

Qwen 3.8 - 27B model support This release adds the support of Qwen 3.8 27B. For Apple Silicon devices, Ollama has in particular optimized for maximum performance and output quality suitable for repeated tasks and…

via github.com
Tuesday, August 11, 2026’s edition
Thursday, July 16, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.1-rc0

Fixes MLX cache leak that could increase memory

What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across requests, and…

via github.com
Wednesday, June 3, 2026’s edition
Wednesday, May 13, 2026’s edition
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc22

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc29

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc15

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc20

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc21

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Ollama — Releases
OLLAMA · 1 source

Ollama v0.30.0-rc31

This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on…

via github.com
Friday, March 27, 2026’s edition
Ollama — Releases
OLLAMA · 1 source

Ollama v0.19.0

Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon is now built on top of Apple’s machine learning framework, MLX, to take advantage of its unified memory architecture…

via github.com
Wednesday, August 19, 2026’s edition
Saturday, August 15, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.14-rc0

Transcodes WebP images for llama-server

What's Changed llm: transcode WebP images for llama-server renderers/qwen: tolerate non-leading system messages Full Changelog: https://github.com/ollama/ollama/compare/v0.32.13...v0.32.14-rc0

via github.com
Friday, August 14, 2026’s edition
Thursday, August 13, 2026’s edition
Tuesday, August 11, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.9

Adds Nemotron 3.5 Lightning open 30B MoE model

NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses like…

via github.com
Tuesday, August 4, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.6-rc0

Speeds up Qwen3.5 on Apple GPUs with speculative decoding

What's Changed Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically `/v1/chat/completions` streaming now matches OpenAI's wire format: `role` only on the…

via github.com
Saturday, July 25, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.4

Adds Laguna on Apple GPUs via MLX engine

What's Changed Support Laguna on Apple GPUs via the MLX engine Quantize draft-model output heads at the requested type when creating speculative-decoding drafts. Fixed Qwen3 MoE decoding for differently-quantized…

via github.com
Thursday, July 23, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.3-rc0

Fixes incomplete GLM tool calls

What's Changed mlx update by @dhiltgen in https://github.com/ollama/ollama/pull/17332 model/parsers: finalize incomplete GLM tool calls by @dhiltgen in https://github.com/ollama/ollama/pull/17250 docs: update…

via github.com
Monday, July 20, 2026’s edition
Ollama — Releases
OLLAMA · v0.32.2

Adds agent skills system

What's Changed launch: keep Claude Code channels available by @hoyyeva in https://github.com/ollama/ollama/pull/17210 cmd: remove dead agent prompt wrappers by @ParthSareen in…

via github.com