unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
Quantization vs meta-llama/Llama-3.2-3B-Instruct. unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit is a quantized version of the other (U8/BF16).
11 derivatives checked
- RRNicole1014/Llama-3.2-3B-Instruct-Profesor-Albus-Dumbledore: Quantization
- nikunjranga/medical-llama-3.2-3b-hf: Quantization
- decaesario/llama3-2-3b-legal-id-sft: Quantization
- Eddienxl/legal-llama-3.2-3b-id-sft: Quantization
- Ryder99/Llama-3.2-3B-Instruct-Hindi: Quantization
- mondk/claude-sonnet5-llama3.2-3b-it: Quantization
- EpistemeAI/ReasoningCore-3B-0: Quantization
- BroneBonBon/Conflict-Generator-Llama-Base: Quantization
- rubuntu/Llama-3.2-3B-Instruct-Jopara-V3: Quantization
- talaviyabhavik/GROOT-3B: Quantization
- talaviyabhavik/GROOT-3B-DPO: Quantization
1 other repos hold byte-for-byte identical weight files.