Ollama - Package Updates

Package Updates

[1.13.6]

Update ollama to 0.30.8
Full Changelog
Fixed ollama launch selecting the wrong provider in some cases
Improved prompt caching by decoupling it from context shift for better KV cache reuse
More stable MLX inference with hardened linear and embedding layers
MLX runner now creates snapshots during prompt processing and speculative decoding for improved reliability
Improved recurrent model support with per-boundary states from the gated-delta kernels
Full Changelog: https://github.com/ollama/ollama/compare/v0.30.7...v0.30.8

Package Updates

[1.13.7]

Update ollama to 0.30.9
Full Changelog
Support for Cohere2Moe architecture
Fixed LFM2 parser/render for cases where thinking was not emitted
Fixed issue where ollama launch claude and other coding agent or assistant use cases would only output one token
Ollama will now return an error if a single message is larger than the current context window
Full Changelog: https://github.com/ollama/ollama/compare/v0.30.8...v0.30.9-rc1

Package Updates

[1.13.8]

Package Updates

[1.13.9]

Update ollama to 0.30.11
Full Changelog
launch: add thinking capability detection to opencode by @hoyyeva in #15434
launch: auto-install Claude Code by @hoyyeva in #16802
launch: auto-install opencode when missing by @hoyyeva in #16806
discover: fix inverted iGPU/dGPU Vulkan classification on Windows hybrid graphics by @Sahil170595 in #16669
mlxrunner: unify and tune speculative decoding by @jessegross in #16791
launch/codex: detect model drift when Codex App UI switches by @BruceMacD in #16864
llama: add sm_86 architecture to cuda_v13_windows preset by @anishesg in #16834
llm: size mmproj offload by projector memory by @dhiltgen in #16866
llm: preserve generation headroom for shifted prompts by @ParthSareen in #16856
llm: fix ollama ps double-counting mmap'd weights on partial offload by @discobot in #16709

Package Updates

[1.14.0]

Update ollama to 0.31.1
Full Changelog
Tightened Gemma 4 MoE model loading in the MLX engine
Updated the MLX engine to the latest version, including a new small-batch matmul kernel
Updated the underlying llama.cpp engine to build 9840
Improved Gemma 4 multi-token prediction (MTP) performance

Package Updates

[1.15.0]

Update ollama to 0.32.0
Full Changelog
New interactive agent experience: running ollama now launches an agent to help you code and delegate work
Renamed the Codex App integration to ChatGPT: use ollama launch chatgpt (and --restore to return to your usual ChatGPT profile)
Simplified integration selection: the ollama launch menu now only offers the most popular integrations (other integrations can be accessed through ollama launch
Warns before launching older agent models: CodeLlama, Qwen2.5(-coder), Llama 3.x, Mistral, StarCoder, and the base DeepSeek-R1 tags now prompt a deprecation warning before ollama launch continues
Full Changelog: https://github.com/ollama/ollama/compare/v0.31.2...v0.32.0

Package Updates

[1.15.1]

Update ollama to 0.32.1
Full Changelog
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 improved cache snapshot performance
MLX text model loading now respects OLLAMA_LOAD_TIMEOUT
Agent web search and fetch now tell users to run ollama signin when authentication is required
The interactive agent now receives the current working directory for better project context
Fixed ollama launch so choosing Pick another model for a deprecated model passed with --model opens the model picker
Updated VS Code setup documentation for the official Ollama extension
Full Changelog: https://github.com/ollama/ollama/compare/v0.32.0...v0.32.1-rc0

Package Updates

[1.15.2]

Update ollama to 0.32.3
Full Changelog
Fixed model downloads that stall before sending data.
Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect --force-build.
Expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs.
Added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix.
Fixed GLM tool calls being silently dropped at the end of generation.
Updated the MLX and llama.cpp engines.
Full Changelog: https://github.com/ollama/ollama/compare/v0.32.1...v0.32.3

Package Updates

[1.15.3]

Update ollama to 0.32.4
Full Changelog
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 experts, plus faster packed gate/up projection (~49% on M5 Max).
Full Changelog: https://github.com/ollama/ollama/compare/v0.32.3...v0.32.4

Package Updates

[1.15.4]

Update ollama to 0.32.5
Full Changelog
Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.

Cloudron Forum