EpistemeAI/ReasoningCore-3B-0
Quantization vs unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit. unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit is a quantized version of the other (U8/BF16).
5 derivatives checked
- mradermacher/ReasoningCore-3B-0-i1-GGUF: Quantization
- mradermacher/ReasoningCore-3B-0-GGUF: Same weights, converted
- DevQuasar-9/EpistemeAI.ReasoningCore-3B-0-GGUF: Same weights, converted
- EpistemeAI/ReasoningCore-3B-RE1-V2: LoRA-style
- EpistemeAI/ReasoningCore-3B-R01: LoRA-style