google/translategemma-27b-it
15 derivatives checked
- mradermacher/translategemma-27b-it-GGUF: Quantization (fewer layers)
- bullerwins/translategemma-27b-it-GGUF: Quantization (fewer layers)
- mradermacher/translategemma-27b-it-i1-GGUF: Quantization (fewer layers)
- kataguru/TranslateGemma-27B-Finnish-GGUF: Quantization (fewer layers)
- mlx-community/translategemma-27b-it-4bit: Quantization
- mlx-community/translategemma-27b-it-8bit: Quantization
- marcosnovaesq/translategemma-27b-it-Q4_K_M-GGUF: Quantization (fewer layers)
- 42ailab/TranslateGemma-27B-GGUF: Quantization (fewer layers)
- DeltaKX/translategemma-27b-it-Q4_K_M-GGUF: Quantization (fewer layers)
- henry1477/translategemma-27b-it-NVFP4A16: Quantization
- mlx-community/translategemma-27b-it-6bit: Quantization
- mlx-community/translategemma-27b-it-bf16: Same weights, repacked (fewer layers)
- kataguru/TranslateGemma-27B-Finnish-W4A16-AWQ: Quantization
- yeoj34760/translategemma-27b-it-Q4_K_M-GGUF: Quantization (fewer layers)
- kaitchup/translategemma-27b-it-FP8-Dynamic: Quantization
2 other repos hold byte-for-byte identical weight files.