JetBrains/Mellum2-12B-A2.5B-Thinking
21 derivatives checked
- JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M: Quantization
- bartowski/Mellum2-12B-A2.5B-Thinking-GGUF: Same weights, converted
- mradermacher/Mellum2-12B-A2.5B-Thinking-i1-GGUF: Quantization
- cyankiwi/Mellum2-12B-A2.5B-Thinking-AWQ-INT4: Quantization
- yuxinlu1/Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF: Full fine-tune
- JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0: Quantization
- JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-MXFP4_MOE: Quantization
- mradermacher/Mellum2-12B-A2.5B-Thinking-GGUF: Quantization
- JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q6_K: Quantization
- JSchneemann/Mellum2-12B-A2.5B-Thinking-GGUF: Same weights, converted
- jedisct1/Mellum2-12B-A2.5B-Thinking-mlx-4bit: Quantization
- mlx-community/Mellum2-12B-A2.5B-Thinking-4bit: Quantization
- Myric/Mellum2-12B-A2.5B-Thinking-APEX-GGUF: Quantization
- DevQuasar/JetBrains.Mellum2-12B-A2.5B-Thinking-GGUF: Quantization
- RedHatAI/Mellum2-12B-A2.5B-Thinking-speculator.dflash: Partial fine-tune
- CodeFault/Mellum2-12B-A2.5B-Thinking-GGUF: Quantization
- RedHatAI/Mellum2-12B-A2.5B-Thinking-NVFP4: Quantization
- rpatel622/Mellum2-12B-A2.5B-Thinking-Dflash-GGUF-FIXED: Partial fine-tune
- mlx-community/Mellum2-12B-A2.5B-Thinking-mxfp4: Quantization
- JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-BF16: Same weights, converted
- josephmayo/Mellum2-12B-A2.5B-Thinking-Abliterated: Abliterated
2 other repos hold byte-for-byte identical weight files.