unsloth/Qwen2.5-3B-Instruct-bnb-4bit
Quantization vs Qwen/Qwen2.5-3B-Instruct. unsloth/Qwen2.5-3B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
17 derivatives checked
- Phora68/rapha: Partial fine-tune
- GSMS-B/Indian-Legal-Qwen2.5-3B-GGUF: Quantization
- freakzy-spec/Legal-Qwen-SFT-Indo: Quantization
- Sweaterdog/Smol-reason2.1: Quantization
- Sweaterdog/Smol-reason2: Quantization
- truongtn2003/vo-danh-qwen2.5: Quantization
- maxrajiv-buda/ira-dolphin: Quantization
- Luimas/claim-extractor-detective-qwen3b: Quantization
- LazyLoopStudio/Nomi-1-Creative: Quantization
- Baked/legal-slm-sft-merged16bit: Quantization
- bqbbao6/Qwen2.5-3B-legal-vn: Quantization
- MSuryakumar/kuralmind-qwen2.5-3b: Quantization
- MuhHendri12/qwen2.5-3b-legal-id-sft: Quantization
- stevensama73/Qwen2.5-3B-sft-think-indonesian: Quantization
- piik/Qwen-2.5-3B-Indonesian-Legal-SFT: Quantization
- RasolKhaled/Ray-3B-IQ_LLM: Quantization
- thanhkt/Qwen2.5-3B-MultiChat-Vi: Adapter
1 other repos hold byte-for-byte identical weight files.