Qwen/Qwen3-235B-A22B-Thinking-2507
19 derivatives checked
- Qwen/Qwen3-235B-A22B-Thinking-2507-FP8: Quantization
- unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF: Same weights, converted
- bartowski/Qwen_Qwen3-235B-A22B-Thinking-2507-GGUF: Quantization
- Mungert/MiroThinker-1.7-mini-GGUF: Not comparable yet
- miromind-ai/MiroThinker-1.7-mini: Different architecture
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-MLX-8bit: Quantization
- John1604/Qwen3-235B-A22B-Thinking-2507-gguf: Quantization
- QuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ: Quantization
- nvidia/Qwen3-Nemotron-235B-A22B-GenRM: Full fine-tune
- nvidia/Qwen3-Nemotron-235B-A22B-GenRM-2603: Full fine-tune
- nvidia/Qwen3-235B-A22B-Thinking-2507-NVFP4: Quantization
- nvidia/Qwen3-235B-A22B-Thinking-2507-Eagle3: Different architecture
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-GGUF: Quantization
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-MLX-4bit: Quantization
- DevQuasar/Qwen.Qwen3-235B-A22B-Thinking-2507-GGUF: Quantization
- lmstudio-community/Qwen3-235B-A22B-Thinking-2507-MLX-6bit: Quantization
- miromind-ai/MiroThinker-1.7: Full fine-tune
- miromind-ai/MiroThinker-v1.5-235B: Full fine-tune
- snwy/frankenqwen3-8B-235B-dense-conversion-interleaved-untuned: Different architecture
9 other repos hold byte-for-byte identical weight files.