OsaurusAI/Raptor-v0.5-8B-A1B-JANG_6M

Quantization vs inclusionAI/Ling-3.0-tiny. OsaurusAI/Raptor-v0.5-8B-A1B-JANG_6M is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse