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.
Llama3-ChatQA-1.5-8BLlama3-ChatQA-1.5-70BLlama3-ChatQA-1.5-8B-GGUFllama-3-nvidia-ChatQA-1.5-8BLlama3-ChatQA-1.5-8B-256K-Q4_K_M-GGUFLlama3-ChatQA-1.5-8B-256Knvidia_-_Llama3-ChatQA-1.5-8B-8bitsChatQA-1.5-8B-AWQnvidia_-_Llama3-ChatQA-1.5-8B-4bitsLlama3-ChatQA-1.5-70B-4.0bpw-h6-exl2Llama3-ChatQA-1.5-8B-ov-int8Llama3-ChatQA-1.5-70B-AWQ-4bitLlama3-ChatQA-1.5-8B-5.0bpw-h6-exl2Llama3-ChatQA-1.5-8B-6.0bpw-h6-exl2Llama3-ChatQA-1.5-70B-2.4bpw-h6-exl2Llama3-ChatQA-1.5-8B-AWQChatQA-1.5-8B-AWQ-4bitLlama3-ChatQA-1.5-8B-4bitLlama3-ChatQA-1.5-8B-bpw4.2-exl2Llama3-ChatQA-1.5-70B-4.65bpw-h6-exl2nvidia-Llama3-ChatQA-1.5-8B-Molecule16Llama3-ChatQA-1.5-8B-vllm-fp8Llama3-ChatQA-1.5-8B-3.0bpw-h6-exl2Llama3-ChatQA-1.5-8B-4.0bpw-h6-exl2Llama3-ChatQA-1.5-70B-3.5bpw-h6-exl2Llama3-ChatQA-1.5-8B-8.0bpw-h8-exl2Llama3-ChatQA-1.5-70B-5.0bpw-h6-exl2Llama3-ChatQA-1.5-70B-6.0bpw-h6-exl2Llama3-ChatQA-1.5-8B-v2-vllm-fp8llama3-chatqa-1.5-8b