Qwen/Qwen3-235B-A22B
24 derivatives checked
- nvidia/Qwen3-235B-A22B-NVFP4: Quantization
- Qwen/Qwen3-235B-A22B-FP8: Quantization
- unsloth/Qwen3-235B-A22B-GGUF: Same weights, converted
- null-space/Qwen3-235B-A22B-abliterated-FP8: Quantization
- Qwen/Qwen3-235B-A22B-GGUF: Quantization
- mlx-community/Qwen3-235B-A22B-4bit: Quantization
- unsloth/Qwen3-235B-A22B-128K-GGUF: Same weights, converted
- Mungert/Homunculus-GGUF: Not comparable yet
- Qwen/Qwen3-235B-A22B-GPTQ-Int4: Quantization
- lmstudio-community/Qwen3-235B-A22B-GGUF: Quantization
- mlx-community/Qwen3-235B-A22B-8bit: Quantization
- QuantFactory/Homunculus-GGUF: Not comparable yet
- QuixiAI/Qwen3-235B-A22B-AWQ: Quantization
- DevQuasar/Qwen.Qwen3-235B-A22B-GGUF: Quantization
- baichuan-inc/Baichuan-M3-235B: Full fine-tune
- RedHatAI/Qwen3-235B-A22B-NVFP4: Quantization
- nvidia/Qwen3-235B-A22B-Eagle3: Different architecture
- baichuan-inc/Baichuan-M3-235B-GPTQ-INT4: Quantization
- nvidia/Qwen3-235B-A22B-FP8: Quantization
- arcee-ai/Homunculus: Different architecture
- ggml-org/Qwen3-235B-A22B-GGUF: Same weights, converted
- justinjja/Qwen3-235B-A22B-INT4-W4A16: Quantization
- AIArchiveInfo/Baichuan-M3-235B: Full fine-tune
- null-space/Qwen3-235B-A22B-abliterated: Abliterated
9 other repos hold byte-for-byte identical weight files.