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.
Qwen3.8-27B-GSQ-RCO-GGUFgemma-3-27b-it-GPTQ-4b-128gQwen3.8-Flash-Next-GSQ-RCO-GGUFistationMistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128ggemma-3-12b-it-GPTQ-4b-128gISTA-DASLab-Qwen3.8-27B-GSQ-RCO-GGUF-Unsloth-MTPQwen3.8-27B-3Bit-GSQQwen3.6-35B-A3B-2Bit-GSQQwen3.5-4B-GGUF-GSQQwen3-8B-GGUF-GSQISTA-DASLab_-_Meta-Llama-3-8B-Instruct-ggufISTA-DASLab-Meta-Llama-3-8B-Instruct-GGUFgemma-3-4b-it-GPTQ-4b-128gLlama-3.1-8B-Instruct-GGUFKimi-K2.5-2Bit-GSQLlama-2-7b-AQLM-2Bit-2x8-hfLlama-3.1-8B-Instruct-FPQuant-QAT-NVFP4Llama-3.2-1B-Instruct-GGUFLlama-3.1-8B-Instruct-FPQuant-QAT-MXFP4Qwen3-4B-GGUF-GSQLlama-2-7b-AQLM-2Bit-1x16-hfgemma-4-e2b-it-istara-ux-research-MLX-F16Llama-2-7b-AQLM-PV-2Bit-2x8-hfQwen3.8-27B-NVFP4-prefillerMeta-Llama-3-70B-AQLM-2Bit-1x16Mixtral-8x7b-AQLM-2Bit-1x16-hfKimi-K2.6-2Bit-GSQAQLM-executorchQwen2.5-7B_single_emb
