Gemma 4 31B It Official is an open-source language model by SevenOfNine. Features: 31b LLM, VRAM: 62.6GB, License: apache-2.0.
Model Card on HF 🤗: https://huggingface.co/SevenOfNine/Gemma-4-31B-It-Official
Gemma 4 31B It Official Parameters and Internals
| LLM Name | Gemma 4 31B It Official |
| Repository 🤗 | https://huggingface.co/SevenOfNine/Gemma-4-31B-It-Official |
| Base Model(s) | |
| Model Size | 31b |
| Required VRAM | 62.6 GB |
| Updated | 2026-05-03 |
| Maintainer | SevenOfNine |
| Model Type | gemma4 |
| Model Files | |
| Model Architecture | Gemma4ForConditionalGeneration |
| License | apache-2.0 |
| Transformers Version | 5.5.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
Best Alternatives to Gemma 4 31B It Official
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 4 31B IT NVFP4 | 0K / 32.6 GB | 1611755 | 425 |
| Gemma 4 31B It | 0K / 62.6 GB | 46845 | 13 |
| Gemma 4 31B It Abliterated | 0K / 62.5 GB | 4744 | 17 |
| Gemma 4 31B It Bf16 | 0K / 62.6 GB | 7225 | 4 |
| Gemma4 GarnetV2 31B | 0K / 62.6 GB | 573 | 9 |
| G4 MeroMero 31B | 0K / 62.6 GB | 6 | 12 |
| Gemma 4 31B JANG 4M CRACK | 0K / 22.6 GB | 2514 | 3 |
| Gemopus 4 31B It | 0K / 62.6 GB | 576 | 7 |
| Gemma4 Garnet 31B | 0K / 62.6 GB | 497 | 9 |
| Gemma 31B Sft 250 | 0K / 62.5 GB | 149 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SevenOfNine/Gemma-4-31B-It-Official .
Rank the Gemma 4 31B It Official Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53407 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a