What's Changed (this repo branch)
Sync to Ollama main v0.6.7
What's Changed (from Ollama)
New models
- Qwen 3: Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
- Phi 4 reasoning and Phi-4-mini-reasoning: New state-of-the-art reasoning models from Microsoft
- Llama 4: state-of-the-art multi-modal models from Meta
What's Changed
- Add support for Meta's Llama 4 multimodal models
- Add support for Microsoft's Phi 4 reasoning models, and Phi 4 mini reasoning model
- Increased default context window to 4096 tokens
- Fixed issue where image paths would not be recognized with ~ when being provided to ollama run
- Improved output quality when using JSON mode in certain scenarios
- Fixed tensor->op == GGML_OP_UNARY errors when running a model due to conflicting inference libraries
- Fixed issue where model would be stuck in the Stopping... state
New Contributors
- @greengrass821 made their first contribution in ollama#10339
- @richardshiue made their first contribution in ollama#10335
- @aduermael made their first contribution in ollama#10386
Full Changelog: v0.6.5...v0.6.7