google/gemma-4-E4B
30 derivatives checked
- google/gemma-4-E4B-it: Full fine-tune
- mradermacher/gemma-4-E4B-GGUF: Same weights, converted (fewer layers)
- unsloth/gemma-4-E4B: Identical copy
- Mungert/gemma-4-E4B-it-GGUF: Full fine-tune (fewer layers)
- RedHatAI/gemma-4-E4B-it: Full fine-tune
- Lythri/Lythri-7B-A4B: Full fine-tune (fewer layers)
- OS-Software/gemma-4-E4B-it-uncensored-heretic-GGUF: Full fine-tune (fewer layers)
- mradermacher/gemma-4-E4B-i1-GGUF: Quantization (fewer layers)
- Roborn/Gemini-3.1-pro-Gemma-4-E4B-Distill: Full fine-tune
- ggml-org/gemma-4-E4B-GGUF: Same weights, converted (fewer layers)
- Cannae-AI/Gemini-3.1-pro-Gemma-4-E4B-Distill: Full fine-tune
- Zainab-Jamshaid/Gemini-3.1-pro-Gemma-4-E4B-Distill: Full fine-tune
- diarizers-community/DiarizationLM-Gemma-4-E4B-v1: Full fine-tune
- majentik/gemma-4-E4B-RotorQuant-GGUF-IQ4_XS: Quantization (fewer layers)
- majentik/gemma-4-E4B-RotorQuant-GGUF-Q4_K_M: Quantization (fewer layers)
- 0penAGI/0pen: Full fine-tune
- SandLogicTechnologies/gemma-4-E4B-GGUF: Full fine-tune (fewer layers)
- Animateus/gemma-4-E4B-GGUF: Quantization (fewer layers)
- Peter-A-P/smallprint-4b-gguf: Full fine-tune (fewer layers)
- majentik/gemma-4-E4B-RotorQuant-GGUF-Q3_K_M: Quantization (fewer layers)
- majentik/gemma-4-E4B-RotorQuant-GGUF-Q8_0: Quantization (fewer layers)
- Felldude/gemma-4-E4B-uncensored: Full fine-tune
- majentik/gemma-4-E4B-RotorQuant-GGUF-Q5_K_M: Quantization (fewer layers)
- majentik/gemma-4-E4B-RotorQuant-GGUF-Q2_K: Quantization (fewer layers)
- zanish-labs/gemma-4-E4B-it-Q4_K_M-gguf: Full fine-tune (fewer layers)
- JMingo/gemma-4-E4B-it-GGUF: Full fine-tune (fewer layers)
- Phonsiri/Thai-Legal-Gemma-4B-CPT: Partial fine-tune
- TheUmbraWalker/gemma-4-E4B-it-2-heretic: Full fine-tune
- Peter-A-P/smallprint-4b: LoRA-style
- thai00/hypegemma-4-e4b: Full fine-tune
30 other repos hold byte-for-byte identical weight files.