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.
DeepScaleR-1.5B-PreviewDeepScaleR-1.5B-Preview-GGUFDeepScaleR-1.5B-Preview-GGUFDeepScaleR-1.5B-Preview-GGUFVinnnf_Thinkless-1.5B-RL-DeepScaleR-GGUFDeepScaleR-1.5B-6.5bitDeepScaleR-1.5B-Preview-unsloth-bnb-4bitSegue-Qwen3_DeepScaleR-Preview-Q4_K_M-GGUFThinkless-1.5B-RL-DeepScaleRDeepScaleR-1.5B-Preview-mlxRAIF-DeepScaleR-1.5BDeepScaleR-1.5B-Preview-16bitDeepScaleR-1.5B-Preview-4bitDeepScaleR-1.5B-PreviewDeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326deepscaler-1.5b-8k-dapo-hard-step400-hfSFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26DeepScaleR-8KDeepScaleR-1.5B-Preview-thinkprune-4kdeepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-400-chkpt-step-300deepscaler-1.5b-8k-dapo-easy-step400-hfDeepScaleR-1.5B-Preview-Q8DeepScaleR-1.5B-Preview-ReproduceQwen3-1.7B-base-Open-R1-GRPO_deepscaler_acc_8192deepscaler-1.5b-8k-easy-first-run-with-shuffle-8k-400-chkpt-step-200deepscaler-1.5b-8k-dapo-random-step200-hfDeepScaleR-1.5B-Preview-8bit-mlxQwen2.5-Math-1.5B-Open-R1-GRPO_deepscaler_mu_8_constant_lrDeepScaleR-1.5B-Preview-Q4_K_M-GGUF