kymv1/Kinyarwanda-ChatGPT-7B
Quantization vs unsloth/Qwen2.5-7B-Instruct-bnb-4bit. unsloth/Qwen2.5-7B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
2 derivatives checked
- mradermacher/Kinyarwanda-ChatGPT-7B-i1-GGUF: Quantization
- mradermacher/Kinyarwanda-ChatGPT-7B-GGUF: Same weights, converted