O
v0.34.2
What's Changed llama.cpp updates Full Changelog: v0.34.1...v0.34.2-rc0
O
v0.34.2-rc0: llama.cpp: version bump b10969 (#18446)
llama.cpp build changes resulted in duplicate symbols between libllama and libmtmd. This moves the compat patch into libllama with exported symbols.
O
v0.34.1
What's Changed MLX safetensors ollama create no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. Improved MLX memory handling on Apple Silicon Runaway repeat token detection now requires 100 repeat tokens for reduced false positives (e.g. OCR) /api/tags is much faster on large model libraries (3.1 s → 294 ms cold in testing),…
O
v0.34.1-rc2: API: Deprecate typical_p (#18448)
Drop support for creating new models with typical_p parameters, while retaining support for existing GGUF models with the setting.
O
v0.34.1-rc1
mlx: add mlx patch to docker build context (#18440)
O
v0.34.1-rc0: MLX: version bump (#18235)
MLX: version bump mlx: support ModelOpt global scales in MoE models address comments address comments
O
v0.34.0
Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction. Full Changelog: v0.33.3...v0.34.0
O
v0.34.0-rc5
openai: support standalone named function outputs (#18348)
O
v0.34.0-rc4
proxy: normalize namespaced commands in Full Access (#18331)
O
v0.34.0-rc3
openai: accept plaintext-labeled Codex agent messages (#18329)
O
v0.34.0-rc2
openai: finalize responses at the web search limit (#18328)
O
v0.34.0-rc1
app: harden Codex desktop proxy handling (#18244)
O
v0.34.0-rc0
app: add Ollama to ChatGPT Desktop (#18236)
O
v0.33.3
What's Changed gemma4 now supports images and audio on MLX engine Report cached prompt tokens Honor GGUF model defined default parameters MLX, MLX-C, llama.cpp update New Contributors @marcelpetrick made their first contribution in #17579 Full Changelog: v0.33.2...v0.33.3
O
v0.33.3-rc2: gemma4: image and audio input support
Safetensors gemma4 imports served by the MLX engine now answer image and audio chats. Images run through both vision architectures: the transformer tower (26B, 31B, e-series) and the 12B's encoder-free unified embedder. Audio arrives through the same intake the ollama API already accepts for gemma4 GGUFs — WAV bytes in the images field, OpenAI input_audio parts, and /v1/audio/transcriptions upload…
O
v0.33.3-rc1
llama.cpp: version bump b10760 (#18199)
O
v0.33.3-rc0: llama.cpp: version bump b10729 (#18160)
llama.cpp: version bump b10729 Regenerate the compat hooks patch for b10729: upstream removed the whole-tensor load_data_for read (last consumer was llama-quantize, which now reads slabs via load_data_range). Keep the existing hook surface (constructor, skip loops, load_all_data, mtmd/clip) unchanged and add maybe_load_text_tensor_range, which materializes a text load op's output once per tensor a…
O
v0.33.2
What's Changed Ollama's app now follows the system appearance again, restoring dark mode support Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one The Claude Desktop proxy no longer interrupts in-flight requests when the model catalog updates Full Changelog: v0.33.1...v0.33.2
O
v0.33.2-rc1
app: list account cloud models for Claude (#18077)
O
v0.33.2-rc0
app: synchronize macOS app handoff (#18056)
O
v0.33.1
What's Changed MLX: Qwen3.8 Flash Next support cmake: make external compat patches idempotent MLX and llama.cpp update mlxrunner: add structured output support mlxrunner: avoid Metal GPU timeouts when loading models from slow storage New Contributors @pd95 made their first contribution in #17948 Full Changelog: v0.33.0...v0.33.1
O
v0.33.1-rc1: linux: fix llama.cpp docker build (#18040)
Build context was missing the new cmake common utility.
O
v0.33.1-rc0: MLX: Qwen3.8 Flash Next support (#18032)
MLX: Qwen3.8 Flash Next support review comments
O
v0.33.0
What's Changed Claude Desktop Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider. Improved caching Fixed a hang where agent clients that cancel long prefills Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting…
O
v0.33.0-rc4
proxy: preserve string content during image fallback (#18002)
O
v0.33.0-rc3
app: add Claude Desktop model mappings (#17979)
O
v0.33.0-rc2
app: prevent Apps title bar overlap (#17925)
O
v0.33.0-rc1
app: sign model recommendation endpoint (#17919)
O
v0.33.0-rc0
app: claude model management (#17915)
O
v0.32.15
What's Changed New desktop onboarding flow on first launch Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks) Fixes a bug where chat and generate could wedge after a mid-stream parser error Qwen 3.8 system messages are now normalized so non-leading system messages are handled consistently MLX and llama.c…