google/gemma-4-31B
25 derivatives checked
- google/gemma-4-31B-it: Full fine-tune
- Mungert/gemma-4-31B-it-GGUF: Full fine-tune (fewer layers)
- mradermacher/gemma-4-31B-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-31B-i1-GGUF: Quantization (fewer layers)
- ggml-org/gemma-4-31B-GGUF: Same weights, converted (fewer layers)
- unsloth/gemma-4-31B: Identical copy
- katiyardinesh/gemma-4-31B-it-custom: Full fine-tune
- majentik/gemma-4-31B-RotorQuant-GGUF-IQ4_XS: Quantization (fewer layers)
- cloudbjorn/gemma-4-31B-Opus-4.6-Reasoning-GGUF: Quantization (fewer layers)
- ipsarkar/gemma-4-31B-GGUF: Quantization (fewer layers)
- thoughtworks/Gemma-4-31B-Eagle3: Different architecture
- majentik/gemma-4-31B-RotorQuant-GGUF-Q4_K_M: Quantization (fewer layers)
- majentik/gemma-4-31B-RotorQuant-GGUF-Q5_K_M: Quantization (fewer layers)
- majentik/gemma-4-31B-RotorQuant-GGUF-Q2_K: Quantization (fewer layers)
- Dev-Louislu/gemma-4-31B-Q4_K_M-GGUF: Quantization (fewer layers)
- majentik/gemma-4-31B-TurboQuant-MLX-4bit: Quantization
- majentik/gemma-4-31B-RotorQuant-GGUF-Q3_K_M: Quantization (fewer layers)
- tianrui6641/gemma-4-31b-gguf-mxfp4: Quantization (fewer layers)
- majentik/gemma-4-31B-RotorQuant-GGUF-Q8_0: Quantization (fewer layers)
- xlr8harder/aria-gemma4-31b-v1: Full fine-tune
- bugrabilge/Omni-31B-Turkish-Reasoning-Model: Full fine-tune
- trashpanda-org/gemma-4-31b-larkspur-v1: Full fine-tune
- callmegrr/gemma-4-31B-it-heretic-z: Full fine-tune
- edgerunner-ai/gemma-4-31B-it-noloop: Full fine-tune
- Pranavz/gemma-4-31B-it-arli: Full fine-tune
26 other repos hold byte-for-byte identical weight files.