DevQuasar/nvidia.Cosmos-Reason2-32B-GGUF

Quantization (fewer layers) vs nvidia/Cosmos-Reason2-32B. DevQuasar/nvidia.Cosmos-Reason2-32B-GGUF matches part of nvidia/Cosmos-Reason2-32B (707 of its 1058 tensors; the rest of nvidia/Cosmos-Reason2-32B has no counterpart). On the shared part: DevQuasar/nvidia.Cosmos-Reason2-32B-GGUF is a GGUF quantization (Q2_K) of the same weights: 257 tensors match exactly and 450 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse