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-int8_float16madlad400-3b-mt-ct2-int8_float16madlad400-3b-mt-ct2-int8_float16madlad400-7b-mt-bt-ct2-int8_float16madlad400-10b-mt-ct2-int8_float16Meta-Llama-3.2-8B-Instruct-ct2-int8_float16nllb-200-3.3B-ct2-int8_float16madlad400-10b-mt-ct2-int8-float16faster-whisper-large-v2-int8_float16Defog_llama-3-sqlcoder-8b-ct2-int8_float16m2m100-12B-last-ckpt-ct2-int8_float16Meta-Llama-3-8B-Instruct-ct2-int8_float16WizardCoder-Python-13B-V1.0-ct2-int8_float16WizardCoder-Python-7B-V1.0-ct2-int8_float16vegam-whisper-medium-ml-int8_float16LaMini-Flan-T5-248M-ct2-int8-float16typhoon-ocr1.5-2b-int8multilingual-e5-small-ct2-int8_float16bce-embedding-base_v1-ct2-int8_float16mpt-30b-instruct-ct2-int8_float16whisper-odia-small-finetune-int8_float16-ct2Meta-Llama-3.1-8B-Instruct-ct2-int8_float16deepset-mxbai-embed-de-large-v1-ct2-int8_float16bge-reranker-base-ct2-int8_float16bge-reranker-v2-m3-ct2-int8_float16ALMA-7B-ct2-int8_float16ALMA-13B-ct2-int8_float16bge-large-en-v1.5-ct2-int8_float16e5-small-v2-ct2-int8_float16snowflake-arctic-embed-m-v2.0-ct2-int8_float16