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.
glm-4-9b-0414-parity-4bit-mlxglm-4-9b-0414-parity-q4_k_m-gguflfm2-350m-parity-q4_k_m-ggufllama-3.2-1b-instruct-parity-bf16-mlxSFT_cumulative_parity_length_16_bitwidth_1_1024_512_Qwen2-1.5B_epoch_25_global_step_100SFT_cumulative_parity_length_16_bitwidth_1_1024_512_Llama-3.2-1B_epoch_3_global_step_12hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1gemma-3-1b-it-parity-bf16-mlxhr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_merged_v1lfm2-350m-parity-4bit-mlxolmo2-7b-instruct-parity-q8_0-ggufolmo2-7b-instruct-parity-8bit-mlxSFT_parity_Qwen2-0.5B_epoch_5_global_step_20gemma-3-1b-it-parity-f16-ggufllama-3.2-1b-instruct-parity-f16-ggufmistral-7b-instruct-v0.3-parity-f16-ggufhr_hand_crafted_Llama-3.3-70B_medium_parity_100_epochs_merged_v1mistral-7b-instruct-v0.3-parity-bf16-mlxolmo-7b-instruct-hf-parity-bf16-mlxSFT_parity_Qwen2-0.5B_epoch_5_global_step_15SFT_parity_Qwen2-0.5B_epoch_2_global_step_6SFT_cumulative_parity_length_16_bitwidth_1_512_512_Qwen2-1.5B_epoch_100_global_step_200SFT_parity_Qwen2-0.5B_epoch_4_global_step_12SFT_parity_length_64_bitwidth_1_256_128_Qwen2-0.5B_epoch_50_global_step_50SFT_cumulative_parity_length_32_bitwidth_1_1024_512_Qwen2-1.5B_epoch_100_global_step_400SFT_parity_Qwen2-0.5B_epoch_0_global_step_0SFT_cumulative_parity_length_16_bitwidth_1_512_512_Qwen2-1.5B_epoch_14_global_step_28SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_100_global_step_800SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_8_global_step_64SFT_cumulative_parity_length_32_bitwidth_1_2048_512_Qwen2-1.5B_epoch_100_global_step_800