Gemma 4 12B It is an open-source language model by unsloth. Features: 12b LLM, VRAM: 23.9GB, License: apache-2.0, LLM Explorer Score: 0.36.
| LLM Name | Gemma 4 12B It |
| Repository 🤗 | https://huggingface.co/unsloth/gemma-4-12b-it |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 23.9 GB |
| Updated | 2026-07-18 |
| Maintainer | unsloth |
| Model Type | gemma4_unified |
| Model Files | |
| Model Architecture | Gemma4UnifiedForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Transformers Version | 5.10.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...le5 Composer2.5 V1 Abliterated | 0K / 24 GB | 15868 | 0 |
| Gemma 4 12B StyleTune | 0K / 25.9 GB | 708 | 23 |
| Gemma 4 12B It Bf16 | 0K / 23.9 GB | 1285 | 5 |
| Gemma 4 12B It Untied | 0K / 25.9 GB | 44 | 0 |
| ...r Fable5 Composer2.5 V1 Sft V5 | 0K / 23.9 GB | 128 | 0 |
| ...r Fable5 Composer2.5 V1 Sft V4 | 0K / 23.9 GB | 106 | 0 |
| Gemma4 12B IT Abliterated | 0K / 24 GB | 112 | 2 |
| ...le5 Composer2.5 V1 Sft V5 Grpo | 0K / 23.9 GB | 24 | 0 |
| Gemma 4 12B It OptiQ 4bit | 0K / 8.8 GB | 16775 | 39 |
| Gemma 4 12B It 4bit | 0K / 10.9 GB | 23981 | 13 |
🆘 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! 🌟