Model Card on HF 🤗: https://huggingface.co/Vikhrmodels/gemma3-vikhr-4b
Gemma3 Vikhr 4B 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)
Gemma3 Vikhr 4B Parameters and Internals
| LLM Name | Gemma3 Vikhr 4B |
| Repository 🤗 | https://huggingface.co/Vikhrmodels/gemma3-vikhr-4b |
| Model Size | 4b |
| Required VRAM | 7.8 GB |
| Updated | 2025-07-29 |
| Maintainer | Vikhrmodels |
| 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 Gemma3 Vikhr 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Typhoon2.1 Gemma3 4B | 128K / 7.8 GB | 70028 | 5 |
| Gemma 3 4B It Abliterated V2 | 128K / 15.5 GB | 3405 | 8 |
| Nile Chat 4B | 128K / 7.8 GB | 317 | 15 |
| EEVE Rosetta 4B 2507 | 128K / 7.8 GB | 27 | 2 |
| Gemma 3 4B Novision | 128K / 7.8 GB | 2918 | 5 |
| Gemma 3 4B Tigrinya | 128K / 7.8 GB | 524 | 0 |
| Medgemma 4B It Abliterated | 128K / 7.8 GB | 27 | 3 |
| Amoral Gemma3 4B V2 | 128K / 8.6 GB | 35 | 2 |
| Amoral Gemma3 4B V1 | 128K / 8.6 GB | 2403 | 16 |
| Amoral Gemma3 4B | 128K / 8.6 GB | 335 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than Vikhrmodels/gemma3-vikhr-4b .
Rank the Gemma3 Vikhr 4B 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? 50262 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124