Qwen/Qwen3.8-27B
1,260 derivatives checked
- unsloth/Qwen3.8-27B-GGUF: Same weights, converted
- Qwen/Qwen3.8-27B-FP8: Quantization
- prism-ml/Ternary-Bonsai-2-27B-gguf: Full fine-tune
- lmstudio-community/Qwen3.8-27B-MLX-4bit: Quantization
- lmstudio-community/Qwen3.8-27B-MLX-8bit: Quantization
- lmstudio-community/Qwen3.8-27B-MLX-6bit: Quantization
- lmstudio-community/Qwen3.8-27B-MLX-5bit: Quantization
- cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF: Quantization
- JonathanColetti/Qwen3.8-27B-Uncensored-GGUF: Quantization
- ggml-org/Qwen3.8-27B-GGUF: Same weights, converted
- huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF: Full fine-tune
- unsloth/Qwen3.8-27B-NVFP4: Quantization
- HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF: Quantization
- autotrust/JEV-27B-VL: Identical copy
- peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF: Quantization
- ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF: Quantization
- byteshape/Qwen3.8-27B-GGUF: Quantization
- 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF: Abliterated
- lmstudio-community/Qwen3.8-27B-GGUF: Quantization
- RadixArk/Qwen3.8-27B-NVFP4: Quantization
- Inferact/Qwen3.8-27B-NVFP4: Quantization
- OBLITERATUS/Qwen3.8-27B-OBLITERATED: Full fine-tune
- nvidia/Qwen3.8-27B-NVFP4: Quantization
- RedHatAI/Qwen3.8-27B-INT4: Quantization
- mlx-community/Qwen3.8-27B-4bit: Quantization
- cyankiwi/Qwen3.8-27B-AWQ-INT4: Quantization
- bartowski/Qwen3.8-27B-GGUF: Same weights, converted
- sakamakismile/Qwen3.8-27B-MTP-NVFP4: Quantization
- gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090: Quantization
- z-lab/Qwen3.8-27B-DFlash2-GGUF: Not comparable yet
146 other repos hold byte-for-byte identical weight files.