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-w4a16-asym-torchao-v0.17.0Llama-3.1-8B-Instruct-w4a16-asym-torchao-v0.17.0Phi-4-reasoning-plus-w4a16-asym-torchao-v0.17.0ptdbench-verl-implementation-torch-functionaltriplee-torchtune_1B_full_finetuned_llama3.2_millfield_241219_meta_header_word_1epoch-GGUFLlama-3.1-8B-Instruct-w4a16-tao-symgroup-torchao-v0.17.0torchwright-doom-e1m1torchwright-calculator-simple-max-digits-9torchwright-calculator-advanced-max-digits-3torchwright-calculator-advanced-max-digits-12torchwright-calculator-simple-max-digits-12torchwright-calculator-scratchpad-max-digits-3torchwright-calculator-simple-max-digits-3torchwright-calculator-memorize-max-digits-2torchwright-calculator-advanced-max-digits-9torchwright-calculator-scratchpad-max-digits-6torchwright-calculator-simple-max-digits-6torchwright-calculator-advanced-max-digits-6Qwen3.5-9B-da8w8-torchao-v0.17.0Qwen3.5-9B-w4a16-tao-symgroup-torchao-v0.17.0Llama-3.1-8B-Instruct-da8w8-torchao-v0.17.0torchwright-doom-e1m1-80x50bart_left_heading_torchgpt-oss-20b-BF16-w4a16-asym-torchao-v0.17.0gemma-3-270m-it-torchao-FP8HybridMoRMoELlama-3.1-8B-Instruct-da8w8-torchao-v0.16.0Qwen3-8B-NVFP4-safetensorsgpt-oss-20b-BF16-da8w8-torchao-v0.17.0Qwen3-14B-Instruct-da8w8-torchao-v0.16.0