unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Quantization vs meta-llama/Llama-3.2-1B-Instruct. unsloth/Llama-3.2-1B-Instruct-bnb-4bit is a quantized version of the other (BF16/U8).
18 derivatives checked
- Sigrex/Llama-3.2-1B-Instruct-tg-signal-extract: Quantization
- MehdiHosseiniMoghadam/AVA-Llama3.2-1B: Quantization
- Tristepin/llma32-3b-zscript3b-test-f: Quantization
- fs90/Llama-3.2-1B-Instruct-bnb-4bit-lima-GGUF: Quantization
- Fyandono/chatbot-id: Adapter
- nith24/llama-3.2-1b-routing-merged: Quantization
- volumetrader/model: Quantization
- NotASI/FineTome-Llama3.2-1B-0929: Quantization
- ssnym/llama-3.2-1b-text-to-sql: Adapter
- dat-lequoc/vLLM-fast-apply-16bit-v0.13-Llama3.2-1B: Quantization
- FrancescoBuda/Llama-ICD-coder-1B-merged: Quantization
- dat-lequoc/fast-apply-16bit-v0.13.1-Llama3.2-1B: Quantization
- dat-lequoc/vLLM-fast-apply-16bit-v0.12-Llama3.2-1B: Quantization
- JefiRyan/Llama-3.2-1B-bnb-4bit-soulcare_no_serialization_4000_steps: Quantization
- disi-unibo-nlp/llama3.2-1B-SFT-medqa-triples-cot: Quantization
- ishan4o4/Ovels-1B: Quantization
- MURUGAYESU/tamil-govt-scheme-Llama-3.2-1B: Quantization
- JefiRyan/Llama-3.2-1B-bnb-4bit-soulcare_no_serialization: Quantization
3 other repos hold byte-for-byte identical weight files.