Mihenk LLM v2 35B (Turkish Financial)
35B MoE (3B active) tuned specifically for Turkish financial-services text — bank statements, investment research, accounting terminology. Niche-cluster model from the Turkish fintech community.
Overview
35B MoE (3B active) tuned specifically for Turkish financial-services text — bank statements, investment research, accounting terminology. Niche-cluster model from the Turkish fintech community.
Strengths
- Domain-specialized — fluent in Turkish finance vocabulary that general models stumble on
- MoE 3B-active keeps inference cost reasonable for the 35B total
- Only Turkish-finance-tuned open model in the catalog
Weaknesses
- License unverified — confirm before any commercial use
- General-purpose tasks may underperform vs Trendyol/YTU mainline models
- Niche audience; small community validation
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 19.3 GB | 25 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Mihenk LLM v2 35B (Turkish Financial).
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Mihenk LLM v2 35B (Turkish Financial)?
Can I use Mihenk LLM v2 35B (Turkish Financial) commercially?
What's the context length of Mihenk LLM v2 35B (Turkish Financial)?
Source: huggingface.co/emircansevdi/Mihenk-LLM-v2-35B-A3B-Turkish-Financial
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Mihenk LLM v2 35B (Turkish Financial) runs on your specific hardware before committing money.