concedo/GLM-ASR-Nano-2512-GGUF

Same weights, converted (fewer layers) vs zai-org/GLM-ASR-Nano-2512. concedo/GLM-ASR-Nano-2512-GGUF matches part of zai-org/GLM-ASR-Nano-2512 (255 of its 745 tensors; the rest of zai-org/GLM-ASR-Nano-2512 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse