Qwen/Qwen3-VL-30B-A3B-Instruct
42 derivatives checked
- QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ: Quantization
- cyankiwi/Qwen3-VL-30B-A3B-Instruct-AWQ-4bit: Quantization
- Qwen/Qwen3-VL-30B-A3B-Instruct-FP8: Quantization
- Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF: Same weights, converted
- unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF: Same weights, converted
- browser-use/bu-30b-a3b-preview: Full fine-tune
- lmstudio-community/Qwen3-VL-30B-A3B-Instruct-GGUF: Quantization
- bartowski/Qwen_Qwen3-VL-30B-A3B-Instruct-GGUF: Same weights, converted
- ig1/Qwen3-VL-30B-A3B-Instruct-NVFP4: Quantization
- huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated: Partial fine-tune
- unsloth/Qwen3-VL-30B-A3B-Instruct-1M-GGUF: Same weights, converted
- Mungert/bu-30b-a3b-preview-GGUF: Full fine-tune
- N8Programs/Unslopper-GGUF: LoRA-style
- mradermacher/Qwen3-VL-30B-A3B-Instruct-i1-GGUF: Quantization
- inference-optimization/Qwen3-VL-1.0B-A0.4B-Instruct: Full fine-tune (fewer layers)
- mradermacher/Qwen3-VL-30B-A3B-Instruct-GGUF: Quantization
- dark-side-of-the-code/Qwen3-VL-30B-A3B-Instruct-AWQ: Quantization
- tripolskypetr/Qwen3-VL-30B-A3B-Instruct-GGUF: Same weights, converted
- MBZUAI/MediX-R1-30B: Full fine-tune
- redponike/Qwen3-VL-30B-A3B-Instruct-GGUF: Quantization
- unsloth/Qwen3-VL-30B-A3B-Instruct: Identical copy
- Intel/Qwen3-VL-30B-A3B-Instruct-int4-AutoRound: Quantization
- ggml-org/Qwen3-VL-30B-A3B-Instruct-Q8_0-GGUF: Quantization
- John1604/Qwen3-VL-30B-A3B-Instruct-gguf: Quantization
- EigenLabs/Qwen3-VL-30B-A3B-Instruct-MLX-4bit: Quantization
- cmh/Jan-v2-VL-max-Instruct-FP8-GGUF: Partial fine-tune
- DevQuasar/Qwen.Qwen3-VL-30B-A3B-Instruct-GGUF: Quantization
- OpenMOSE/Qwen3-VL-REAP-24B-A3B: Same weights, repacked
- Hugguf/Qwen3-VL-30B-A3B-Instruct-GGUF: Quantization
- EnderCrypt/Qwen3-VL-30B-A3B-Instruct-GGUF-mmproj: Quantization
8 other repos hold byte-for-byte identical weight files.