alpha-ai/Deep-Reason-SMALL-V0
Quantization vs unsloth/Llama-3.2-3B-Instruct-bnb-4bit. unsloth/Llama-3.2-3B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
2 derivatives checked
- mradermacher/Deep-Reason-SMALL-V0-i1-GGUF: Quantization
- mradermacher/Deep-Reason-SMALL-V0-GGUF: Same weights, converted