Qwen/Qwen3.8-2.4T-A95B
30 derivatives checked
- nvidia/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- Qwen/Qwen3.8-2.4T-A95B-FP8: Quantization
- unsloth/Qwen3.8-2.4T-A95B-GGUF: Same weights, converted
- Inferact/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- inference-optimization/Qwen3.8-1.0B-A0.6B: Different architecture
- RadixArk/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-50: Quantization
- RedHatAI/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-25: Quantization
- pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap60-3bit: Quantization
- anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0: Quantization
- kernelpool/Qwen3.8-2.4T-A95B-3bit-UVMAX: Quantization
- pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap50-3bit: Quantization
- RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-FP8: Quantization
- pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap75-4bit: Quantization
- Inferact/Qwen3.8-2.4T-A95B-MXFP4: Quantization
- a4lg/Qwen3.8-2.4T-A95B-MTP-ONLY-GGUF: Not comparable yet
- nota-ai/Qwen3.8-2.4T-A95B-Nota-NVFP4-Global-Pruned-40: Quantization
- dudeman2512/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- RedHatAI/Qwen3.8-2.4T-A95B-FP8: Quantization
- modal-labs/Qwen3.8-2.4T-A95B-NVFP4: Quantization
- dudeman2512/Qwen3.8-2.4T-A95B-FP8: Quantization
- dudeman2512/Qwen3.8-2.4T-A95B-int4: Quantization
- Vaibhavhome30/Qwen3.8-2.4T-A95B-FP8: Quantization
- LilacGhost10/Qwen3.8-2.4T-A95B-FP8: Quantization
- vs4vijay/Qwen3.8-2.4T-A95B-FP8: Quantization
- iceDonkey/Qwen3.8-2.4T-A95B-FP8: Quantization
- Blackfrost-AI/Qwen-3.8-2.4T-A95B-Derisked-IQ1_0-GGUF: Quantization
- DevQuasar/Qwen.Qwen3.8-2.4T-A95B-GGUF: Quantization
- neopolita/Qwen3.8-84B-A53B-Niwaki-v2-experimental-mlx: Quantization
20 other repos hold byte-for-byte identical weight files.