unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
Quantization vs Qwen/Qwen2.5-Coder-7B-Instruct. unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
19 derivatives checked
- bekoozkan/godot-qwen2.5-coder-7b-instruct-bnb-4bit: Adapter
- face00/qwen2.5-7b-security-cot: Quantization
- Nsnshs/qwen2.5-coder-uncensored: Quantization
- Chama29929/chamindu-ai-7b-16bit: Quantization
- NadevA23/Kronumos: Quantization
- BugTraceAI/BugTraceAI-CORE-Fast: Quantization
- igarin/Qwen2.5-Coder-7B-20260302-GGUF: Quantization
- igarin/Qwen2.5-Coder-7B-20260219-GGUF: Quantization
- khoin68/Qwen2.5-Coder-7B-Vietnamese-LoRA: Adapter
- AviralGusain/unity-debug-coach: Quantization
- akshatkot/linus-coder: Partial fine-tune
- goodnessolayinka/oadson-cli-subagent-lora-v2: Quantization
- Axilotal/cadquery-qwen2.5-7b-v5.2-hardened: Quantization
- igarin/Qwen2.5-Coder-7B-20260218-GGUF: Different architecture
- neph1/Qwen2.5-Coder-7B-Instruct-Unity: Quantization
- smirki/UIGEN-T1.1-Qwen-7B: Quantization
- anupbth1/Ved-Code-7B: Quantization
- dtometzki/Qwen2.5-Interviewer-7B: Quantization
- onekq-ai/OneSQL-v0.1-Qwen-7B: Adapter
2 other repos hold byte-for-byte identical weight files.