q4 · llm
Kimi K2.5 (4-bit)
mlx-community
Mixture-of-experts language model from Moonshot AI, 1T parameters with 32B active.
◆ huggingface.co
details →
mlx models.
sourced.
ready to run.
Converted and quantized weights for Apple Silicon. Every entry links straight back to the repo it came from.
q4 · llm
Qwen3 8B (4-bit)
mlx-community
General-purpose chat model from Qwen.
◆ huggingface.co
details →
q4 · llm
Ornith 1.5 9B (4-bit)
ornith-ai
Dense 9B language model from ornith-ai for chat and text generation.
◆ huggingface.co
details →
q4 · llm
Qwen2.5 Coder 7B Instruct (4-bit)
mlx-community
Code model from Qwen for writing, completing and explaining code.
◆ huggingface.co
details →
q4 · llm
DeepSeek R1 0528 Qwen3 8B (4-bit)
lmstudio-community
Reasoning model: DeepSeek R1 distilled into Qwen3 8B.
◆ huggingface.co
details →