meta-llama/Llama-3.2-3B
76 derivatives checked
- unsloth/Llama-3.2-3B: Identical copy
- lemuralabs/Llama-3.2-3B-Uncensored-GGUF: Full fine-tune
- HumeAI/tada-3b-ml: Full fine-tune (fewer layers)
- nvidia/llama-nv-embed-reasoning-3b: Full fine-tune
- Mungert/Dolphin3.0-Llama3.2-3B-GGUF: Full fine-tune
- QuantFactory/Dolphin3.0-Llama3.2-3B-GGUF: Full fine-tune
- unsloth/Llama-3.2-3B-bnb-4bit: Quantization
- dbaysal/metallama3.2-3b-learned: Adapter
- QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF: Full fine-tune
- Shyamnath/Llama-3.2-3b-Uncensored-GGUF: Full fine-tune
- dphn/Dolphin3.0-Llama3.2-3B: Full fine-tune
- ABDALLALSWAITI/llm_3_2_flux_prompt: LoRA-style
- QuantFactory/Llama-3.2-Taiwan-3B-GGUF: Full fine-tune
- michelkao/Ollama-3.2-GGUF: LoRA-style
- yothinS/Llama-3.2-3B-Thai_CRM: LoRA-style
- OctoThinker/OctoThinker-8B-Long-Base: Different architecture
- OctoThinker/OctoThinker-3B-Hybrid-Base: Full fine-tune
- deepcogito/cogito-v1-preview-llama-3B: Full fine-tune
- oopere/pruned40-llama-3.2-3b: Same weights, converted
- DevQuasar/Llama-3.2-3B-GGUF: Quantization
- oopere/pruned20-llama-3.2-3b: Same weights, converted
- Open4bits/Llama-3.2-3B-GGUF: Quantization
- OctoThinker/OctoThinker-8B-Hybrid-Base: Different architecture
- Gurubot/self-after-dark-3b: LoRA-style
- oopere/pruned10-llama-3.2-3B: Same weights, converted
- davezaxh/llama-3.2-exp: Full fine-tune
- oopere/pruned60-llama-3.2-3b: Same weights, converted
- ericflo/Llama-3.2-3B-COT: Partial fine-tune
- adidsh/indic-speak-int8-onnx: Full fine-tune
- lastmass/llama3.2-chinese: Full fine-tune
24 other repos hold byte-for-byte identical weight files.