Arxiv:2501.13944 Ar Autotrain compatible En Endpoints compatible Gemma2 Pytorch Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/QCRI/Fanar-1-9B
Fanar 1 9B 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)
Fanar 1 9B Parameters and Internals
| LLM Name | Fanar 1 9B |
| Repository 🤗 | https://huggingface.co/QCRI/Fanar-1-9B |
| Model Size | 9b |
| Required VRAM | 18.6 GB |
| Updated | 2025-07-20 |
| Maintainer | QCRI |
| Model Type | gemma2 |
| Model Files | |
| Supported Languages | ar en |
| Model Architecture | Gemma2ForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Fanar 1 9B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| G2 GSHT 32K | 32K / 20.4 GB | 8 | 1 |
| SystemGemma2 9B It | 32K / 18.6 GB | 17 | 2 |
| Gemma 2 9B It SimPO | 8K / 18.6 GB | 21863 | 168 |
| Gemma 2 9B It | 8K / 18.6 GB | 107255 | 720 |
| Gemma 2 9B | 8K / 37.1 GB | 90700 | 661 |
| ...2 9B Cpt Sahabatai V1 Instruct | 8K / 18.6 GB | 2719 | 44 |
| Magnolia V3 Gemma2 8K 9B | 8K / 18.6 GB | 899 | 3 |
| SILMA 9B Instruct V1.0 | 8K / 18.6 GB | 24561 | 75 |
| Darkest Muse V1 | 8K / 20.4 GB | 1020 | 83 |
| Fanar 1 9B Instruct | 8K / 17.7 GB | 4779 | 23 |
Note: green Score (e.g. "73.2") means that the model is better than QCRI/Fanar-1-9B .
Rank the Fanar 1 9B 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124