Model Card on HF 🤗: https://huggingface.co/scb10x/typhoon2.1-gemma3-12b
Typhoon2.1 Gemma3 12B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Typhoon2.1 Gemma3 12B Parameters and Internals
| LLM Name | Typhoon2.1 Gemma3 12B |
| Repository 🤗 | https://huggingface.co/scb10x/typhoon2.1-gemma3-12b |
| Model Size | 12b |
| Required VRAM | 23.4 GB |
| Updated | 2025-11-19 |
| Maintainer | scb10x |
| Model Type | gemma3_text |
| Model Files | |
| Model Architecture | Gemma3ForCausalLM |
| License | gemma |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.50.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262145 |
| Torch Data Type | bfloat16 |
Best Alternatives to Typhoon2.1 Gemma3 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 3 12B It Abliterated V2 | 128K / 47.2 GB | 1461 | 10 |
| Nile Chat 12B | 128K / 23.4 GB | 1123 | 11 |
| Gemma 3 Coldbrew Test1 | 128K / 23.4 GB | 5 | 0 |
| Gemma 3 Glitter 12B | 128K / 23.4 GB | 139 | 7 |
| Gemma 3 Starshine 12B Alt | 128K / 23.4 GB | 4 | 6 |
| Gemma 3 Confetti 12B | 128K / 23.4 GB | 8 | 3 |
| G3 12B Inkstruct Epoch2 | 128K / 23.4 GB | 5 | 0 |
| ... 12B Storyteller V0.2 Textonly | 128K / 23.4 GB | 5 | 5 |
| Glitterfetti Merge C | 128K / 29 GB | 6 | 0 |
| G3 12B Rp System V0.1 | 128K / 23.4 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than scb10x/typhoon2.1-gemma3-12b .
Rank the Typhoon2.1 Gemma3 12B 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? 51555 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124