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.
Qwen3.5-9B-Q1_0-GGUFqwen2-0.5B-4bit-q1Qwen3.5-0.8B-Q1_0-GGUFWeiver-Q1-4B-GGUFphi-3-8bit_Q16_0_ggDeepSeek-R1-Distill-Qwen-7B-Q4_K_M-GGUFDeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M-GGUFQ15H10M-0000Qwen3-8B-Base-FP8q1-Qwen2.5-0.5bQ15H10M-0000-GGUFDeepSeek-R1-Distill-Qwen-1.5B-Q8_0-GGUFq1-Qwen2.5-0.5b-Instructq101q102q104model_2025_01_14_q16_e3_15b_lora128model_2025_01_14_q16_e1_15b_lora256Qwen3-8B-Base-float8Qwen3-8B-Base-INT8-INT4granite-summary-loramodel_2025_01_14_q16_e3_15b_lora256daint_prod_q1_k2-16_abl_1N4n_fa344ca4_step-00230000comp0264-partb-q1-style-classifierdaint_prod_q1_k2-16_abl_1N4n_81607a4b_step-00230000Qwen3-8B-Base-INT4comp0264-partb-q1-style-classifiervit_epochs5_batch32_lr5e-05_size224_tiles12_seed2_q1gpu_q14B_prometheus1e-3-c0c0vit_epochs5_batch32_lr5e-05_size224_tiles2_seed1_q1
