unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
Quantization vs Qwen/Qwen2.5-1.5B-Instruct. unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
18 derivatives checked
- fox3000foxy/Luna-Protocol-1.5B-Discord-Dialogues-50k-instruct: Quantization
- samudradino/pgabl-legal-chatbot: Quantization
- fox3000foxy/Luna-Protocol-1.5B-Discord-Dialogues-200k-instruct: Quantization
- ppsub/PhishDetectAI-GRPO: Quantization
- RamBhogesara/vera-qwen-1.5b-dpo: Quantization
- aletta2206/legal-chatbot-finetuned: Quantization
- bbuttercup/legal-chatbot-qwen2.5-1.5b-id: Quantization
- Shreyaallupati/qwen2.5-1.5b-merchant-agent: Quantization
- agentbyumer/qwen2.5-1.5b-reasoning-GGUF: Quantization
- Avadhut7777/vision-finetuned: Quantization
- IzNrsydn/legal-chatbot-llama3-finetuned: Quantization
- GSMS-B/Indian-Legal-Qwen2.5-1.5B-GGUF: Quantization
- ameliacndr10/legal-chatbot-llama3-finetuned: Quantization
- thanhkt/Qwen2.5-1.5B-Vi-Alpaca: Adapter
- Shahansha/Manthan-1.5B-sft: Quantization
- QwexGP/QAi-2.0: Quantization
- Jenil05/Aether-1.5B-Agentic-core: Quantization
- Rithaji-AI/Rithaji-1.5B: Quantization
1 other repos hold byte-for-byte identical weight files.