mradermacher/Qwen3-VL-4B-Spatial-Analysisv2-GGUF

Same weights, converted (fewer layers) vs sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv2. mradermacher/Qwen3-VL-4B-Spatial-Analysisv2-GGUF matches part of sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv2 (398 of its 713 tensors; the rest of sabaridsnfuji/Qwen3-VL-4B-Spatial-Analysisv2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse