google/gemma-3n-E4B-it
Partial fine-tune vs google/gemma-3n-E4B. Partial change: 88% of the weights changed (attention, embeddings, mlp, norms, other), in 35 of 35 layers.
Tensors changed: Attention 140/363, Embeddings 11/25, Norms 247/489, other 281/687, MLP 108/112
32 derivatives checked
- google/gemma-3n-E2B-it: Partial fine-tune
- unsloth/gemma-3n-E4B-it: Identical copy
- unsloth/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/gemma-3n-E4B-it-MLX-bf16: Same weights, repacked
- bartowski/google_gemma-3n-E4B-it-GGUF: Quantization (fewer layers)
- mlx-community/gemma-3n-E4B-it-lm-4bit: Quantization
- yujiepan/gemma-3n-tiny-random: Different architecture
- yujiepan/gemma-3n-tiny-random-dim4: Different architecture
- unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit: Quantization
- tripolskypetr/gemma-3n-e4b-it: Same weights, converted (fewer layers)
- second-state/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- Sci-fi-vy/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- mmnga/gemma-3n-E4B-it-gguf: Quantization (fewer layers)
- fibonacciai/RealRobot-Chatbot-Ecommerce-Robot-Fibonacci-Nano-llm: Full fine-tune
- mradermacher/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- gaianet/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- DevQuasar/google.gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- tatsuyaaaaaaa/gemma-3n-E4B-it-gguf: Same weights, converted (fewer layers)
- mradermacher/gemma-3n-E4B-it-i1-GGUF: Quantization (fewer layers)
- BaybeDragon/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- RedHatAI/gemma-3n-E4B-it-FP8-dynamic: Quantization
- BaybeDragon/genmyanmar-3-E4B-it-GGUF: Same weights, converted (fewer layers)
- olegshulyakov/gemma-3n-E4B-it-GGUF: Quantization (fewer layers)
- mlx-community/gemma-3n-E4B-it-lm-bf16: Same weights, repacked (fewer layers)
- huihui-ai/Huihui-gemma-3n-E4B-it-abliterated: Partial fine-tune
- Qwe1325/gemma-3n-E4B-it-GGUF: Same weights, converted (fewer layers)
- MuXodious/gemma-3n-E4B-it-absolute-heresy-MPOA: Partial fine-tune
- MuXodious/gemma-3n-E4B-it-PaperWitch-heresy: Partial fine-tune
- MuXodious/gemma-3n-E4B-it-less-heretic: Partial fine-tune
- MuXodious/gemma-3n-E4B-it-absolute-heresy: Partial fine-tune
3 other repos hold byte-for-byte identical weight files.