Qwen/Qwen-Drive-1.0-4B
Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 4/4, MLP 189/196, Attention 296/320, Norms 172/203
6 derivatives checked
- Hob-forge/Qwen-Drive-1.0-4B-GGUF: Not comparable yet
- drivetechodyssey/Qwen-Drive-1.0-4B-VLM-mlx-8bit: Quantization
- timm/qwen3_vit_306m.qwen_drive_1_0_4b: Different architecture
- drivetechodyssey/Qwen-Drive-1.0-4B-VLM-mlx-bf16: Different architecture
- timm/qwen3_vit_306m_enc.qwen_drive_1_0_4b: Different architecture
- drivetechodyssey/Qwen-Drive-1.0-4B-VLM-mlx-4bit: Quantization
2 other repos hold byte-for-byte identical weight files.