XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Full fine-tune vs Qwen/Qwen3.5-9B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 4/4, MLP 207/208, Attention 309/332, Norms 210/215
70 derivatives checked
- bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF: Same weights, converted
- Hikari07jp/MiMo-V2.6-Distill-Qwen-9B-Ablitrated: LoRA-style
- ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUF: Quantization
- BoldingBuilds/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF: Full fine-tune
- ngquocvinh/MiMo-V2.6-Distill-Qwen-9B-GGUF: Quantization
- mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit: Quantization
- wepiqx/MiMo-V2.6-Distill-Qwen-9B-GGUF-MERNIK: Quantization
- prithivMLmods/MiMo-V2.6-Distill-Qwen-9B-GGUF: Same weights, converted
- mradermacher/MiMo-V2.6-Distill-Qwen-9B-i1-GGUF: Quantization
- 0xSojalSec/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLX: Full fine-tune
- mradermacher/MiMo-V2.6-Distill-Qwen-9B-GGUF: Same weights, converted
- Youssofal/MiMo-V2.6-Qwen-9B-MTPLX-Optimized-Speed: Quantization
- VitreousCut/MiMo-V2.6-Distill-Qwen-9B-MTP-GGUF: Not comparable yet
- saidutta69/MiMo-V2.6-Distill-Qwen-9B-heretic: Abliterated
- Quantelium/MiMo-V2.6-Distill-Qwen-9B-GGUF: Same weights, converted
- OliviaRossi/MiMo-Ornith-9B-AGSI: Full fine-tune
- ldov/MiMo-V2.6-Distill-Qwen-9B-GGUF: Same weights, converted
- webmp3/Sakura-MiMo-V2.6-Distill-Qwen-9B-GGUF: Quantization
- nativ-community/MiMo-V2.6-Distill-Qwen-9B-MLX-4bit: Quantization
- ramgpt/MiMo-V2.6-Distill-Qwen-9B-GGUF: Quantization
- prithivMLmods/MiMo-V2.6-Distill-Qwen-9B-MLX: Partial fine-tune
- CNWPlayer/MiMo-V2.6-Distill-Qwen-9B-Q4_K_M-GGUF: Quantization
- nativ-community/MiMo-V2.6-Distill-Qwen-9B-MLX-8bit: Quantization
- cyankiwi/MiMo-V2.6-Distill-Qwen-9B-AWQ-BF16-INT4: Quantization
- VladHong/Qwen3.5-9B-Ornimo-SLERP-GGUF: Full fine-tune
- thegovind/blink-mimo-9b: LoRA-style
- OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-HQ: Full fine-tune
- sakamakismile/MiMo-V2.6-Distill-Qwen-9B-GGUF: Quantization
- ddalcu/MiMo-V2.6-Distill-Qwen-9B-MLX-Serve-6bit: Quantization
- TaskPuppyAI/TPAI-MiMo-v2.6-Qwen-9B-2-GGUF: Full fine-tune
6 other repos hold byte-for-byte identical weight files.