Model Card on HF 🤗: https://huggingface.co/ToastyPigeon/g3-12b-inkstruct-epoch2
G3 12B Inkstruct Epoch2 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)
G3 12B Inkstruct Epoch2 Parameters and Internals
| LLM Name | G3 12B Inkstruct Epoch2 |
| Repository 🤗 | https://huggingface.co/ToastyPigeon/g3-12b-inkstruct-epoch2 |
| Model Size | 12b |
| Required VRAM | 23.4 GB |
| Updated | 2025-04-28 |
| Maintainer | ToastyPigeon |
| Model Type | gemma3_text |
| Model Files | |
| Model Architecture | Gemma3ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262208 |
| Torch Data Type | bfloat16 |
Best Alternatives to G3 12B Inkstruct Epoch2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Fallen Gemma3 12B V1 | 128K / 24.3 GB | 413 | 16 |
| Gemma 3 Glitter 12B | 128K / 23.4 GB | 139 | 7 |
| Gemma 3 Confetti 12B | 128K / 23.4 GB | 66 | 2 |
| ... 12B Storyteller V0.2 Textonly | 128K / 23.4 GB | 8 | 3 |
| G3 12B Rp System V0.1 | 128K / 23.4 GB | 12 | 1 |
| Glitterfetti Merge C | 128K / 29 GB | 12 | 0 |
| Aether Gemma3 12B Beta V1 | 128K / 24.3 GB | 11 | 0 |
| Gemma 3 1B It Abliterated | 32K / 2 GB | 623 | 3 |
| Veritas 12B | 128K / 24.3 GB | 172 | 21 |
| Amoral Gemma3 12B V1 | 128K / 24.3 GB | 407 | 39 |
Note: green Score (e.g. "73.2") means that the model is better than ToastyPigeon/g3-12b-inkstruct-epoch2 .
Rank the G3 12B Inkstruct Epoch2 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? 46763 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227