Qwen 3.5 2B Turkish SFT
Qwen 3.5 2B base with supervised fine-tuning on Turkish instruction-following data. Recent community fine-tune (early 2026) that bridges Qwen 3.5's strong multilingual base with Turkish-specific chat capability.
Overview
Qwen 3.5 2B base with supervised fine-tuning on Turkish instruction-following data. Recent community fine-tune (early 2026) that bridges Qwen 3.5's strong multilingual base with Turkish-specific chat capability.
Strengths
- Modern Qwen 3.5 base — strong tokenizer for Turkish (Qwen ships with 119-language coverage)
- 32K context inherited from Qwen base
- SFT applied on top of an already-multilingual base — preserves general capability
Weaknesses
- Community fine-tune; less production-validation than vendor releases
- 2B size limits depth on complex reasoning
- SFT-only — no preference tuning (RLHF/DPO)
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 | 1.1 GB | 2 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 Qwen 3.5 2B Turkish SFT.
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 Qwen 3.5 2B Turkish SFT?
Can I use Qwen 3.5 2B Turkish SFT commercially?
What's the context length of Qwen 3.5 2B Turkish SFT?
Source: huggingface.co/Tuguberk/Qwen3.5-2B-Turkish-SFT
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Qwen 3.5 2B Turkish SFT runs on your specific hardware before committing money.