Qwen/Qwen3-VL-4B-Instruct
133 derivatives checked
- unsloth/Qwen3-VL-4B-Instruct-GGUF: Same weights, converted (fewer layers)
- Qwen/Qwen3-VL-4B-Instruct-GGUF: Same weights, converted (fewer layers)
- Qwen/Qwen3-VL-4B-Instruct-FP8: Quantization
- unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit: Quantization
- TomoroAI/tomoro-colqwen3-embed-4b: LoRA-style
- lmstudio-community/Qwen3-VL-4B-Instruct-GGUF: Quantization (fewer layers)
- unsloth/Qwen3-VL-4B-Instruct: Identical copy
- cyankiwi/Qwen3-VL-4B-Instruct-AWQ-4bit: Quantization
- JEILDLWLRMA/Qwen3-VL-4B-Instruct-NVFP4: Quantization
- huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated: Abliterated
- OpenSearch-AI/Ops-Colqwen3-4B: LoRA-style
- DreamFast/Qwen3-VL-4b-Heretic-GGUF: Abliterated (fewer layers)
- bartowski/Qwen_Qwen3-VL-4B-Instruct-GGUF: Same weights, converted (fewer layers)
- Mungert/GELab-Zero-4B-preview-GGUF: Full fine-tune (fewer layers)
- cyankiwi/Qwen3-VL-4B-Instruct-AWQ-8bit: Quantization
- furiosa-ai/Qwen3-VL-4B-Instruct: Identical copy
- DreamEternal/MinerU-Popo: Full fine-tune
- unsloth/Qwen3-VL-4B-Instruct-bnb-4bit: Quantization
- guanxuyu/visual-jev-4b-answer-sft: Adapter
- unsloth/Qwen3-VL-4B-Instruct-1M-GGUF: Same weights, converted (fewer layers)
- MCG-NJU/TimeLens2-4B: Partial fine-tune
- prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX: Abliterated
- tanhuajie2001/Robo-Dopamine-GRM-2.0-4B-Preview: Full fine-tune
- robometer/Robometer-4B: Partial fine-tune
- StarVLA/Qwen3-VL-4B-Instruct-Action: Same weights, repacked
- NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct: Adapter
- aisingapore/Qwen-SEA-LION-v4-4B-VL: Full fine-tune
- DreamFast/Qwen3-VL-4b-Heretic: Abliterated
- mradermacher/Qwen3-VL-4B-Instruct-i1-GGUF: Quantization (fewer layers)
- mradermacher/Qwen3-VL-4B-Instruct-GGUF: Same weights, converted (fewer layers)
21 other repos hold byte-for-byte identical weight files.