Ollama - Package Updates

[nebulon]

[0.1.0]

• Initial version for Ollama

[Package Updates]

[0.2.0]

• Update ollama to 0.12.6
• Full Changelog
• Ollama's app now supports searching when running DeepSeek-V3.1, Qwen3 and other models that support tool calling.
• Flash attention is now enabled by default for Gemma 3, improving performance and memory utilization
• Fixed issue where Ollama would hang while generating responses
• Fixed issue where qwen3-coder would act in raw mode when using /api/generate or ollama run qwen3-coder <prompt>
• Fixed qwen3-embedding providing invalid results
• Ollama will now evict models correctly when num_gpu is set
• Fixed issue where tool_index with a value of 0 would not be sent to the model
• Thinking models now support structured outputs when using the /api/chat API
• Ollama's app will now wait until Ollama is running to allow for a conversation to be started
• Fixed issue where "think": false would show an error instead of being silently ignored

[Package Updates]

[0.3.0]

• Fix wrong documentation URL in package info

[Package Updates]

[0.3.1]

• Update ollama to 0.12.7
• Full Changelog
• Qwen3-VL is now available in all parameter sizes ranging from 2B to 235B
• MiniMax-M2: a 230 Billion parameter model built for coding & agentic workflows available on Ollama's cloud
• Ollama's new app now includes a way to add one or many files when prompting the model:
• For better responses, thinking levels can now be adjusted for the gpt-oss models:
• New API documentation is available for Ollama's API: https://docs.ollama.com/api
• Model load failures now include more information on Windows
• Fixed embedding results being incorrect when running embeddinggemma
• Fixed gemma3n on Vulkan backend
• Increased time allocated for ROCm to discover devices
• Fixed truncation error when generating embeddings

[Package Updates]

[0.4.0]

• Update ollama to 0.12.9
• Full Changelog
• Fix performance regression on CPU-only systems

[Package Updates]

[0.5.0]

• Breaking: Move /api and /v1 endpoints to the main domain, to avoid requirement for a secondary domain.
• Breaking: Use OpenAI compatible API key instead of JWT token. See docs for info on how to use that.

[Package Updates]

[1.0.0]

• First stable package release with ollama 0.12.9

[Package Updates]

[1.0.1]

• Update ollama to 0.12.10
• Full Changelog
• ollama run now works with embedding models
• Fixed errors when running qwen3-vl:235b and qwen3-vl:235b-instruct
• Enable flash attention for Vulkan (currently needs to be built from source)
• Add Vulkan memory detection for Intel GPU using DXGI+PDH
• Ollama will now return tool call IDs from the /api/chat API
• Fixed hanging due to CPU discovery
• Ollama will now show login instructions when switching to a cloud model in interactive mode
• Fix reading stale VRAM data

[Package Updates]

[1.0.2]

• Update ollama to 0.12.11
• Full Changelog
• Ollama's API and the OpenAI-compatible API now supports Logprobs
• Ollama's new app now supports WebP images
• Improved rendering performance in Ollama's new app, especially when rendering code
• The "required" field in tool definitions will now be omitted if not specified
• Fixed issue where "tool_call_id" would be omitted when using the OpenAI-compatible API.
• Fixed issue where ollama create would import data from both consolidated.safetensors and other safetensor files.
• Ollama will now prefer dedicated GPUs over iGPUs when scheduling models
• Vulkan can now be enabled by setting OLLAMA_VULKAN=1. For example: OLLAMA_VULKAN=1 ollama serve

[Package Updates]

[1.1.0]

• Update ollama to 0.13.0
• Full Changelog
• DeepSeek-OCR is now supported
• DeepSeek-V3.1 architecture is now supported in Ollama's engine
• Fixed performance issues that arose in Ollama 0.12.11 on CUDA
• Fixed issue where Linux install packages were missing required Vulkan libraries
• Improved CPU and memory detection while in containers/cgroups
• Improved VRAM information detection for AMD GPUs
• Improved KV cache performance to no longer require defragmentation

[Package Updates]

[1.1.1]

• Update ollama to 0.13.1
• Full Changelog
• nomic-embed-text will now use Ollama's engine by default
• Tool calling support for cogito-v2.1
• Fixed issues with CUDA VRAM discovery
• Fixed link to docs in Ollama's app
• Fixed issue where models would be evicted on CPU-only systems
• Ollama will now better render errors instead of showing Unmarshal: errors
• Fixed issue where CUDA GPUs would fail to be detected with older GPUs
• Added thinking and tool parsing for cogito-v2.1

[Package Updates]

[1.1.2]

• Increase the proxy read timeout to 1h

[Package Updates]

[1.1.3]

• Disable body size check within the app

[Package Updates]

[1.1.4]

• Update ollama to 0.13.3

[Package Updates]

[1.1.5]

• Update ollama to 0.13.4
• Full Changelog
• Nemotron 3 Nano: A new Standard for Efficient, Open, and Intelligent Agentic Models
• Olmo 3 and Olmo 3.1: A series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
• Enable Flash Attention automatically for models by default
• Fixed handling of long contexts with Gemma 3 models
• Fixed issue that would occur with Gemma 3 QAT models or other models imported with the Gemma 3 architecture

[Package Updates]

[1.1.6]

• Update ollama to 0.13.5
• Full Changelog
• Google's FunctionGemma is now available on Ollama
• bert architecture models now run on Ollama's engine
• Added built-in renderer & tool parsing capabilities for DeepSeek-V3.1
• Fixed issue where nested properties in tools may not have been rendered properly

[Package Updates]

[1.2.0]

• Update ollama to 0.14.0
• Full Changelog
• ollama run --experimental CLI will now open a new Ollama CLI that includes an agent loop and the bash tool
• Anthropic API compatibility: support for the /v1/messages API
• A new REQUIRES command for the Modelfile allows declaring which version of Ollama is required for the model
• For older models, Ollama will avoid an integer underflow on low VRAM systems during memory estimation
• More accurate VRAM measurements for AMD iGPUs
• Ollama's app will now highlight swift soure code
• An error will now return when embeddings return NaN or -Inf
• Ollama's Linux install bundles files now use zst compression
• New experimental support for image generation models, powered by MLX