google/gemma-3-270m-it
Full fine-tune vs google/gemma-3-270m. Fine-tune: 100% of the weights changed, across 18 of 18 layers.
Tensors changed: Embeddings 1/1, Norms 109/109, MLP 54/54, Attention 72/72
101 derivatives checked
- unsloth/gemma-3-270m-it-GGUF: Same weights, converted
- unsloth/gemma-3-270m-it: Identical copy
- unsloth/gemma-3-270m-it-unsloth-bnb-4bit: Quantization
- bartowski/google_gemma-3-270m-it-GGUF: Same weights, converted
- ggml-org/gemma-3-270m-it-GGUF: Quantization
- gguf-org/gemma-3-270m-it-gguf: Same weights, converted
- lmstudio-community/gemma-3-270m-it-MLX-8bit: Quantization
- mlx-community/gemma-3-270m-it-4bit: Quantization
- lmstudio-community/gemma-3-270m-it-MLX-bf16: Same weights, repacked
- Open4bits/gemma-3-270m-it-gguf: Full fine-tune
- lmstudio-community/gemma-3-270m-it-MLX-4bit: Quantization
- inboxpraveen/Kavach-PII-270M: LoRA-style
- unsloth/gemma-3-270m-unsloth-bnb-4bit: Quantization
- Omokemi/hop-1-gemma-270m: Full fine-tune
- second-state/gemma-3-270m-it-GGUF: Same weights, converted
- Sci-fi-vy/gemma-3-270m-it-GGUF: Same weights, converted
- mlx-community/gemma-3-270m-it-8bit: Quantization
- lmstudio-community/gemma-3-270m-it-GGUF: Same weights, converted
- alpha-ai/Medical-Diagnosis-COT-Gemma3-270M: LoRA-style
- adodabele/FoodExtract-gemma-3-270m-fine-tune-v1: Full fine-tune
- deftgeno/dlp_intents: Full fine-tune
- DevQuasar/google.gemma-3-270m-it-GGUF: Same weights, converted
- jeetxx/FoodExtract-Gemma-3-270M: Full fine-tune
- tatsuyaaaaaaa/gemma-3-270m-it-gguf: Same weights, converted
- pixasocial/survival-uncensored-gemma-270m-v2: LoRA-style
- unsloth/gemma-3-270m-it-bnb-4bit: Quantization
- mlx-community/gemma-3-270m-it-bf16: Same weights, repacked
- mmnga/gemma-3-270m-it-gguf: Quantization
- loom-ai-org/gemma-3-270m-it-loom: Not comparable yet
- Null-Guard/vMAX-Bangla-Gemma3-270m-GGUF: LoRA-style
35 other repos hold byte-for-byte identical weight files.