Fanar 2 27B Instruct is an open-source language model by QCRI. Features: 27b LLM, VRAM: 54.4GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.31.
Arxiv:2501.13944 Arxiv:2603.16397 Ar Base model:finetune:google/gem... Base model:google/gemma-3-27b-... Conversational En Endpoints compatible Gemma3 text Instruct Pytorch Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/QCRI/Fanar-2-27B-Instruct
Fanar 2 27B Instruct 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 2 27B Instruct Parameters and Internals
| LLM Name | Fanar 2 27B Instruct |
| Repository 🤗 | https://huggingface.co/QCRI/Fanar-2-27B-Instruct |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 54.4 GB |
| Updated | 2026-05-14 |
| Maintainer | QCRI |
| Model Type | gemma3_text |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar en |
| Model Architecture | Gemma3ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.55.4 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262208 |
| Torch Data Type | bfloat16 |
Rank the Fanar 2 27B Instruct 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? 53972 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a