google/gemma-4-E4B-it
Full fine-tune vs google/gemma-4-E4B. Fine-tune: 93% of the weights changed, across 42 of 42 layers.
Tensors changed: MLP 126/606, Norms 212/502, other 124/261, Attention 132/755, Embeddings 4/6
289 derivatives checked
- lmstudio-community/gemma-4-E4B-it-MLX-4bit: Quantization
- lmstudio-community/gemma-4-E4B-it-MLX-8bit: Quantization
- lmstudio-community/gemma-4-E4B-it-MLX-6bit: Quantization
- lmstudio-community/gemma-4-E4B-it-MLX-5bit: Quantization
- unsloth/gemma-4-E4B-it-GGUF: Not comparable yet
- ggml-org/gemma-4-E4B-it-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/gemma-4-E4B-it-GGUF: Quantization (fewer layers)
- unsloth/gemma-4-E4B-it-unsloth-bnb-4bit: Quantization
- unsloth/gemma-4-E4B-it: Identical copy
- EldanRing/Winnow-E4B: Not comparable yet
- OBLITERATUS/gemma-4-E4B-it-OBLITERATED: Partial fine-tune
- bartowski/google_gemma-4-E4B-it-GGUF: Same weights, converted (fewer layers)
- unsloth/gemma-4-E4B-it-NVFP4: Quantization
- mlx-community/gemma-4-e4b-it-4bit: Quantization
- cyankiwi/gemma-4-E4B-it-AWQ-INT4: Quantization
- AtomicChat/gemma-4-E4B-it-GGUF: Quantization (fewer layers)
- prithivMLmods/gemma-4-E4B-it-FP8: Quantization
- unsloth/gemma-4-E4B-it-UD-MLX-4bit: Quantization
- batiai/gemma-4-E4B-it-GGUF: Quantization (fewer layers)
- Vishva007/gemma-4-E4B-it-W4A16-AutoRound-GPTQ: Quantization
- google/gemma-4-E4B-it-qat-q4_0-unquantized: Full fine-tune
- pearsonkyle/gemma-4-E4B-imatrix-awq-GGUF: Not comparable yet
- ente-ai/gemma-4-E4B-it-GGUF: Not comparable yet
- bekoozkan/godot-gemma-4-e4b-it-GGUF: LoRA-style (fewer layers)
- MassivDash/Gemma-4-Rust-Coder: Not comparable yet
- saidutta69/gemma-4-E4B-it-heretic: Abliterated
- giladgd/gemma-4-E4B-it-GGUF: Same weights, converted (fewer layers)
- ciocan/gemma-4-E4B-it-W4A16: Quantization
- tiny-random/gemma-4e: Full fine-tune
- ahmed22xa/new-adult-writer-GGUF: Quantization (fewer layers)
116 other repos hold byte-for-byte identical weight files.