MLX

Timeline

1. Oct 11, 2026 · Opinion / analysis · 1 source
   [P] Pecision models that score every allowed label from the logits: Jebadiah v2.1 (27B, 9B), open weights and self-run benchmark results [P]
   I've been building open models that treat a decision as a closed-set scoring problem rather than text generation.
2. Oct 6, 2026 · Research paper · 1 source
   Breaking the Space Barrier and its Application to Language Model Inference
   Language models are more and more often asked for structured output: JSON that follows a schema, or a tool call with typed arguments.
3. Oct 6, 2026 · Open-source release · 1 source
   unslothai/unsloth v0.1.903-beta: New Browser + Voice Cloning
   This release adds a browser inside Unsloth (browser use coming very soon), so files, web pages and pages the model writes open right beside your chat.
4. Oct 1, 2026 · Product / feature launch · 1 source
   unslothai/unsloth v0.1.902-beta: Command Palette + Desktop UI/UX
   This release brings faster navigation, shareable run settings, and clearer errors to Unsloth Desktop.
5. Sep 29, 2026 · Open-source release · 1 source
   ollama/ollama v0.35.1
   Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it.
6. Sep 28, 2026 · Open-source release · 1 source
   ollama/ollama v0.35.0
   Decision models return choices, probabilities, and scores instead of text.
7. Sep 28, 2026 · Open-source release · 1 source
   unslothai/unsloth v0.1.900-beta: Laya Decision Models + Library
   Run and serve Decision Models like Laya (open-source Jev) locally
8. Sep 25, 2026 · Open-source release · 1 source
   ollama/ollama v0.40.0
   Models run on MLX on Apple Silicon by default
9. Sep 23, 2026 · Open-source release · 1 source
   ollama/ollama v0.34.4
   Qwen 3.8 prompt processing is faster on Apple Silicon.
10. Sep 19, 2026 · Open-source release · 1 source
    ollama/ollama v0.34.3
    GET /api/show now advertises each model's thinking controls and default:
11. Sep 15, 2026 · Open-source release · 1 source
    ollama/ollama v0.34.2
    Added first-run setup when running ollama, with options to sign in or continue locally.
12. Sep 14, 2026 · Open-source release · 1 source
    ollama/ollama v0.34.1
    GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization.
13. Sep 2, 2026 · Open-source release · 1 source
    ollama/ollama v0.33.3
    gemma4 now supports images and audio on MLX engine
14. Aug 26, 2026 · Open-source release · 1 source
    ollama/ollama v0.33.1
    mlxrunner: avoid Metal GPU timeouts when loading models from slow storage
15. Aug 21, 2026 · Open-source release · 1 source
    ollama/ollama v0.33.0
    Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
16. Aug 19, 2026 · Open-source release · 1 source
    ollama/ollama v0.32.15
    New desktop onboarding flow on first launch
17. Jun 9, 2026 · Model release · 1 source
    Introducing Gemma 4 12B: a unified, encoder-free multimodal model
    Introducing Gemma 4 12B: a unified, encoder-free multimodal model
18. Apr 6, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.10
    Piecewise CUDA Graph Enabled by Default: Piecewise CUDA graph capture is now the default execution mode, reducing memory overhead and improving throughput for models with complex control flow patterns: #16331
19. Mar 28, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.10rc0
    Piecewise CUDA Graph Enabled by Default: Piecewise CUDA graph capture is now the default execution mode, reducing memory overhead and improving throughput for models with complex control flow patterns: #16331

Often appears with