meta-llama/Llama-3.2-3B-Instruct
295 derivatives checked
- RedHatAI/Llama-3.2-3B-Instruct-FP8-dynamic: Quantization
- unsloth/Llama-3.2-3B-Instruct: Identical copy
- RedHatAI/Llama-3.2-3B-Instruct-FP8: Quantization
- bartowski/Llama-3.2-3B-Instruct-GGUF: Same weights, converted
- MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF: Same weights, converted
- unsloth/Llama-3.2-3B-Instruct-GGUF: Same weights, converted
- lmstudio-community/Llama-3.2-3B-Instruct-GGUF: Quantization
- unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit: Quantization
- unsloth/Llama-3.2-3B-Instruct-bnb-4bit: Quantization
- hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF: Quantization
- QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF: Quantization
- baseten/Llama-3.2-3B-Instruct-pythonic: Identical copy
- Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth: LoRA-style
- unsloth/Llama-3.2-3B-unsloth-bnb-4bit: Quantization
- QuantFactory/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-GGUF: Full fine-tune
- legraphista/Llama-3.2-3B-Instruct-IMat-GGUF: Same weights, converted
- hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF: Quantization
- Mungert/Schematron-3B-GGUF: Full fine-tune
- huluhuluu/llama-3.2-3b-instruct-eagle3-sharegpt-sw512-epoch9-step231810: Different architecture
- huihui-ai/Llama-3.2-3B-Instruct-abliterated: Abliterated
- QuantFactory/Llama3.2-3B-Esper2-GGUF: Full fine-tune
- mlx-community/Llama-3.2-3B-Instruct: Same weights, converted
- QuantFactory/Llama3.2-3B-Enigma-GGUF: Full fine-tune
- lahirum/Llama-3.2-3B-Instruct-Q4_0-GGUF: Quantization
- acon96/Home-Llama-3.2-3B: Full fine-tune
- QuantFactory/Llama-Sentient-3.2-3B-Instruct-GGUF: Full fine-tune
- DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored: Abliterated
- kiel2/Kiel-2.1-Sol: LoRA-style
- second-state/Llama-3.2-3B-Instruct-GGUF: Same weights, converted
- Skywork/Skywork-Reward-V2-Llama-3.2-3B: Full fine-tune
88 other repos hold byte-for-byte identical weight files.