mradermacher/Qwen3-ASR-1.7B-Persian-GGUF

Same weights, converted (fewer layers) vs Neurai/Qwen3-ASR-1.7B-Persian. mradermacher/Qwen3-ASR-1.7B-Persian-GGUF matches part of Neurai/Qwen3-ASR-1.7B-Persian (310 of its 707 tensors; the rest of Neurai/Qwen3-ASR-1.7B-Persian has no counterpart). On the shared part: Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse