v0.1.805-beta

✨ New Features

• Run Qwen3.8-Flash-Next and GLM-5.3-Flash up to 2x faster with MTP (enabled by default).
• Smoother model loading with fewer errors across local servers and connected providers.
• Safer chat edits that preserve tool cards, reply details, and conversation branches.
• New local media APIs for video, audio, and MLX-served models.
• New audio support with models like MiniMax-Music3, Higgs, MOSS, and progress tracking.
• Improved multi-GPU planning, memory fitting, and split-model training.
• Ctrl+F Search now works.
• Strengthened AMD/ROCm detection, installation, and GPU compatibility.
• Upgraded MCP, Deep Research, OAuth, and agent tool reliability.
• GLM tools can now be used across longer, multi-turn chats.
• Qwen automatically applies recommended settings for thinking and non-thinking modes.
• Fine-tune large MoE models with text or images on Apple Silicon using MLX.
• Long Qwen chats run much faster on Mac with follow-up turns up to 30x faster.
• MLX models now use their full context size and support much longer batched generation.
• MLX releases GPU memory more cleanly between generation bursts and model switches.
• Serve MLX models through Unsloth's OpenAI-compatible API.
• Audio clips can now be archived and managed.
• Improved reliability with custom TTS playback fixes, Whisper pairing checks, and stronger audio testing.
• Run several tool calls at once without mixing up their arguments.
• Tools remain available when chatting with images.
• Each chat keeps its MCP connection for faster tool calls.
• Local models can edit code using Codex’s apply_patch tool.
• Continue long chats with images and other media using Auto Compaction.
• Review and approve Deep Research plans before research starts.
• Train larger models across multiple GPUs with automatic placement.
• AMD installs choose the best build across Windows and Linux, with BF16 on more GPUs.
• Export GLM-5.3 MLX fine-tunes to GGUF.
• Choose custom GGUF shard sizes and save locations.
• Generate videos through the new OpenAI-compatible Videos API.
• Choose a custom port for LAN access.
• Model downloads show clearer progress and can switch from Xet to HTTP automatically.
• Studio: add the OpenAI videos API on /v1/videos.
• Pin Claude Code to the loaded model's real context window.
• Studio: list route-aware models through the openai api.
• Studio: add Higgs, MOSS, and MiniMax audio models.
• Studio: render escaped inline math in lists.
• Restore UNSLOTH_RETURN_LOGITS after prediction_step instead of forcing it to 0.
• Studio: update in the background and restart when ready.
• Serve every MiniMax H3 asset from unsloth rather than a community repack.