Fanar Models by Fanar
Fanar releases · 1 in the last 12 monthsChangelog →
1 model2026Up to 32K ctx
Last refreshed 2026-08-27. Next refresh: weekly.
Details
ResearcherFanar
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context32K
About
Fanar Arabic-centric instruction-tuned language models from Qatar Computing Research Institute, continual-trained from Gemma 3.
Decision facts
- Best fit
- General model comparison
- Capability starting point
- Fanar 2 27B Instruct with 32K context
- Lowest tracked input
- Not tracked
- Closest related family
- 360Zhinao
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Fanar 2 27B InstructCurrent
Use when the workload needs 32K context and 27B parameters.
2026-0332K context27B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Fanar 2 27B Instruct | Use when the workload needs 32K context and 27B parameters. | 2026-03 | 32K context27B parameters | Current |
Release Timeline
1 release group2026-03
1 current
Fanar 2 27B Instruct
Current32K context27B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Fanar 2 27B Instruct | 2026-03 | 32K | 27B |