MLX

MLX appears in 19 Vector Wire stories since August, 7 of them about MLX itself.

Stories About MLX

7

Ollama v0.34.1 Patches MLX Memory, Raises Token Repeat LimitBrief · Sep 15

• Sep 17Ollama Fixes MLX Memory Leak in Speculative DecodingAlert · Sep 17
• Sep 14Ollama v0.34.1-rc0 Adds MLX Support for ModelOpt Global Scales in MoE ModelsAlert · Sep 14
• Sep 2Ollama Adds Image and Audio Input for Gemma 4 Safetensors via MLX EngineAlert · Sep 2
• Aug 26Ollama v0.33.1-rc0 Adds MLX Support for Qwen3.8 Flash NextAlert · Aug 26
• Aug 25Apple MLX v0.32.2 Adds NAX Attention, Quantized MOE OptimizationsAlert · Aug 25
• Aug 19Ollama Releases v0.32.15-rc0 With MLX UpdateAlert · Aug 19

More stories about MLX

Also Mentioned In

12

• Oct 17Meta's Muse Spark Open bets 816B parameters on agentic edge over Chinese open-weight rivalsOct 17
• Oct 14LiquidAI ships LFM2.5-24B-A2B, a 24B reasoning model that activates only 2B parametersOct 14
• Oct 6Unsloth Adds Built-in Browser Panel, EmbeddingGemma 2, Audio Tools in v0.1.903 BetaOct 6
• Sep 29Ollama v0.35.1-rc0 Adds Explicit Model Capability DeclarationsSep 29
• Sep 29Ollama v0.35.0 Adds Decision Models via /v1/systemone EndpointSep 29

More stories that mention MLX

• Sep 28Unsloth Adds Local Decision Models, 4.5× Faster Image GenerationSep 28
• Sep 19Ollama v0.34.3 Adds Thinking Controls API, Nemotron H on Apple SiliconSep 19
• Sep 9Unsloth v0.1.808 Delivers 1.7x Faster Diffusion, 250-Plus Bug FixesSep 9
• Sep 2Unsloth Doubles Inference Speed for Qwen3.8-Flash, GLM-5.3-Flash via MTPSep 2
• Aug 26PyTorch Ecosystem Adds 10 Projects Spanning RL, Inference, Survival AnalysisAug 26
• Aug 21Ollama v0.33.0 Adds Claude Desktop App IntegrationAug 21
• Aug 10Meta Releases Muse Glimmer, 30B On-Device Agentic Model via ExecuTorchAug 10