ggml-org/Qwen3-ASR-0.6B-GGUF

Same weights, converted (fewer layers) vs Qwen/Qwen3-ASR-0.6B. ggml-org/Qwen3-ASR-0.6B-GGUF matches part of Qwen/Qwen3-ASR-0.6B (311 of its 612 tensors; the rest of Qwen/Qwen3-ASR-0.6B 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 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse