tencent/Hy-MT2-1.8B
17 derivatives checked
- tencent/Hy-MT2-1.8B-GGUF: Full fine-tune
- tencent/Hy-MT2-1.8B-FP8: Quantization
- unsloth/Hy-MT2-1.8B-GGUF: Same weights, converted
- fumetodev/Hy-MT2-1.8B-JP-Manga-Finetune-v5-GGUF: LoRA-style
- mradermacher/Hy-MT2-1.8B-i1-GGUF: Quantization
- mradermacher/Hy-MT2-1.8B-GGUF: Same weights, converted
- fumetodev/Hy-MT2-1.8B-JP-Manga-Finetune-chinese-zh-Hans-v1-GGUF: LoRA-style
- aidsoid/Hy-MT2-1.8B-MLX-4bit: Quantization
- divingclone/Hy-MT2-1.8B-NVFP4-Q4_K_M-GGUF: Quantization
- alphaZimuth/Hy-MT2-1.8B-SpecDraft-30B: Same weights, converted
- Arm/hy-mt2-1-8b-q4-0-llamacpp-vivo-x300: Same weights, converted
- Poirott/Oshi-Translate-Magshot-GGUF: Not comparable yet
- mlx-community/Hy-MT2-1.8B-Abliterated-8bit: Quantization
- illitan/Hy-MT2-1.8B-4bit: Quantization
- botp/Hy-MT2-1.8B-GGUF: Full fine-tune
- jizhiovo/Hy-MT2-1.8B-mlx-4bit: Quantization
- winninghealth/WiNGPT-Babel-2.2: Full fine-tune
9 other repos hold byte-for-byte identical weight files.