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.
qwen3.6-27b-wanda-structLlama-3.3-70B-Instruct-wanda-unstructLlama-3.3-70B-Instruct-wanda-structgemma-3-12b-it-wanda-unstructqwen3-32b-wanda-unstructqwen3.6-27b-wanda-unstructgemma-3-12b-it-wanda-structLlama-3.1-70B-Instruct-wanda-structured-2-4qwen3-14b-wanda-structLlama-3.1-70B-Instruct-wanda-unstruct-50qwen3-14b-wanda-unstructtest_wanda_240109llama-2-7b_wanda_2_4_gptq_4bit_128gllama-2-7b-saf3pruned-aya-23-35b-wanda-0.5-unstructured-mc4-es-0pruned-aya-23-8b-wanda-0.5-unstructured-mc4-de-0wandaa-v02-mergedwanda25sparsitymodelpruned-pruned-aya-23-35b-wanda-0.5-2to4-mc4-es-0wandaa-v03-mergedwandaa-v04-mergedpruned-llama3-8b-instruct-wanda-0.5-unstructured-mc4-ru-0pruned-aya-23-8b-wanda-0.5-unstructured-mc4-es-0pruned-aya-23-8b-wanda-0.5-unstructured-mc4-zh-0pruned-aya-23-35b-wanda-0.5-unstructured-mc4-ru-0pruned-aya-23-35b-wanda-0.5-unstructured-mc4-sw-0pruned-llama3-70b-instruct-wanda-0.5-unstructured-mc4-zh-0pruned-pruned-aya-23-35b-wanda-0.5-unstructured-mc4-de-0pruned-pruned-aya-23-8b-wanda-0.5-unstructured-mc4-ar-42wanda75sparsitymodel