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.
nllb-200-distilled-600M-ct2-int8nllb-200-distilled-1.3B-ct2-int8m2m100_418M-ct2-int8nllb-200-3.3B-ct2-int8nllb-200-distilled-1.3B-ct2-int8m2m100_1.2B-ct2-int8madlad400-3b-mt-ct2-int8madlad400-3b-ct2-int8m2m_100_418m_ct2_int8SEX_ROLEPLAY-3.2-1B-ao-int8da8wnllb-200-distilled-1.3B-ct2-int8nllb-200-1.3B-ct2-int8LFM2.5-1.2B-Thinking-ToMoE-INT8INT8-nemotron-3.5-asr-streaming-0.6bEXAONE-4.0-1.2B-GPTQ-Int8m2m_100_1.2b_ct2_int8SEX_ROLEPLAY-3.2-1B-ao-int8wo-gs128LFM2.5-350M-ToMoE-INT8ark-asr-0.6b-int8-onnxmadlad400-7b-mt-bt-ct2-int8_float16madlad400-7b-mt-ct2-int8nllb-200-3.3B-int8-ct2meta-llama_Llama-3.1-8B-Instruct-auto_gptq-int8-gs128-symnllb-200-1.3B-int8-ct2madlad400-7b-mt-ct2-int8Llama-3.2-3B-Instruct-ct2-int8meta-llama_Llama-3.2-3B-Instruct-auto_gptq-int8-gs64-asymmeta-llama_Llama-3.2-3B-Instruct-auto_round-int8-gs64-asymmeta-llama_Llama-3.2-3B-Instruct-auto_round-int8-gs64-symmeta-llama_Llama-3.2-3B-Instruct-auto_gptq-int8-gs64-sym