unsloth/Llama-3.2-3B-bnb-4bit
Quantization vs meta-llama/Llama-3.2-3B. unsloth/Llama-3.2-3B-bnb-4bit is a quantized version of the other (U8/BF16).
10 derivatives checked
- bhanuripranathi/LIama-3.2-test-GGUF: Quantization
- RangareddyJulakanti/java-fullstack-interview-model: Quantization
- SuyashKirti96/model_test_5: Quantization
- Fitzeon/llama32-3b-legal-id-sft: Quantization
- jakaria6284/heritageGuide: Quantization
- anilguven/Llama3.2-3b-InstrucTurca-tr-unsloth: Adapter
- Chinnu1103/FineLlama-3.2-3B-GGUF: Quantization
- itsnebulalol/Llama-3.2-Nemotron-3B: Quantization
- JallyAI/Nomi-1.0-3b: Quantization
- EryriLabs/Llama-3.2-SARA-3b: Quantization
2 other repos hold byte-for-byte identical weight files.