Hugging Face's logo

MLX Community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

kernelpool  new activity about 16 hours ago
mlx-community/MiniMax-M2-4bit:MiniMax-M2-4bit not supported
kernelpool  updated a model about 19 hours ago
mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit
saviochow  new activity about 19 hours ago
mlx-community/mlx-my-repo:ERROR:root:Model type minimax not supported.
View all activity

mlx-community 's collections 98

💧LFM2-8B-A1B-MoE
Best in Class MoE, better than Qwen3. Optimised for Smaller devices sub 16 GB (M1/2/3/4) Apple Silicon.
Qwen3-Coder-MoE
💻 Significant Performance: among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving ~Claude Sonnet.
Josiefied and Abliterated Qwen3
Abliterated, and further fine-tuned to be the most uncensored models available. Now in MLX
Gemma 3 QAT
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory.
Josiefied and Abliterated Qwen2.5
The best uncensored models
Qwen1.5
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
ServiceNow-Apriel
Apriel-1.5-15b-Thinker is a multimodal reasoning model in ServiceNow’s Apriel SLM series which achieves competitive performance against models 10 time
MedGemma
Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications.
Gemma 3
A collection of lightweight, state-of-the-art open models built from the same research and technology that powers the Gemini 2.0 models
Qwen2.5
The Qwen 2.5 models are a series of AI models trained on 18 trillion tokens, supporting 29 languages and offering advanced features such as instructio
Llama 3.2
Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models.
💧LFM2-8B-A1B-MoE
Best in Class MoE, better than Qwen3. Optimised for Smaller devices sub 16 GB (M1/2/3/4) Apple Silicon.
ServiceNow-Apriel
Apriel-1.5-15b-Thinker is a multimodal reasoning model in ServiceNow’s Apriel SLM series which achieves competitive performance against models 10 time
Qwen3-Coder-MoE
💻 Significant Performance: among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving ~Claude Sonnet.
MedGemma
Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications.
Josiefied and Abliterated Qwen3
Abliterated, and further fine-tuned to be the most uncensored models available. Now in MLX
Gemma 3 QAT
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory.
Gemma 3
A collection of lightweight, state-of-the-art open models built from the same research and technology that powers the Gemini 2.0 models
Josiefied and Abliterated Qwen2.5
The best uncensored models
Qwen1.5
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
Qwen2.5
The Qwen 2.5 models are a series of AI models trained on 18 trillion tokens, supporting 29 languages and offering advanced features such as instructio
Llama 3.2
Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models.