models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.6-35B-A3B-GPTQ-Int4Qwen3.6-27B-GPTQ-Int4Phi-4-mini-instruct-INT8-INT4Qwen3-4B-INT8-INT4MiniCPM-V-2_6-int4MiniCPM-V-4_5-int4nemotron-3.5-asr-streaming-0.6b-onnx-int4Audio8-TTS-Preview-0.6B-ONNX-INT4Phi-4-mini-instruct-int4-ovMiniCPM-o-2_6-int4Phi-3.5-vision-instruct-int4-ovApertus-v1.1-0.5B-Instruct-QAD-INT4-ONNXApertus-v1.1-4B-Instruct-QAD-INT4-ONNXApertus-v1.1-1.5B-Instruct-QAD-INT4-ONNXPhi-4-mini-instruct-AWQ-INT4KAT-Dev-GPTQ-Int4MOSS-TTS-Local-Transformer-v1.5-awq-int4MiniCPM-V-4-int4InternVL2-1B-int4-ovbge-m3-int4-asym-g64-openvinoInternVL2-2B-int4-ovQwen3-8B-INT4bge-m3-int4-asym-g32-openvinoQwen3-8B-Nemotron-Orchestrator-NOESIS-AWQ-INT4octen-embedding-0.6b-onnx-int4Swift-Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16Apertus-v1.1-4B-Instruct-MLX-INT4qwen3-asr-0.6b-onnx-int4-mergedVoxCPM2-MLX-int4Phi-4-mini-instruct-INT4
