Downloads · 30 days
64
25% of all-time downloads
UgurI/Qwen3.8-27B-Turkish-CPT-GGUF
Qwen3.8-27B-Turkish-CPT-GGUF is a text generation model from UgurI. Use it when you need the model to write or continue text. The card lists the license as cc-by-nc-sa-4.0.
GGUF quantizations for Qwen3.8-27B-Turkish-CPT, adapted for high-quality Turkish comprehension, reasoning, and instruction following.
Downloads · 30 days
64
25% of all-time downloads
All-time downloads
254
Public
Repo size
16.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf16.5 GB · 100%
From the Hugging Face model README
GGUF quantizations for Qwen3.8-27B-Turkish-CPT, adapted for high-quality Turkish comprehension, reasoning, and instruction following.
Qwen/Qwen3.8-27B (Text-only causal LM backbone)Q4_K_M (15.41 GB, 4.92 BPW)| File | Quant Method | File Size | Description |
|---|---|---|---|
Qwen3.8-27B-Turkish-CPT-Q4_K_M.gguf | Q4_K_M | 15.41 GB | Recommended balance of speed, memory (~18 GB VRAM/RAM), and Turkish accuracy |
| Metric | Base Model (Qwen3.8-27B) | Turkish-CPT-GGUF | Improvement |
|---|---|---|---|
| Turkish Validation Perplexity | 7.5838 | 6.9360 | -8.55% |
| Turkish Test Perplexity | 8.0534 | 7.3303 | -8.98% |
| TurkishMMLU (90-Q Stratified) | 60.00% | 75.56% | +15.56% |
| Belebele Reading Comprehension (TR) | 83.33% | 90.00% | +6.67% |
| Belebele Reading Comprehension (EN) | 96.67% | 96.67% | 100% Retained |
Qwen3.8-27B-Turkish-CPT-Q4_K_M.gguf and Modelfile files.ollama create qwen3.8-turkish -f Modelfile
ollama run qwen3.8-turkish
Qwen3.8-27B-Turkish-CPT-Q4_K_M.gguf into your LM Studio models directory.llama-cli -m Qwen3.8-27B-Turkish-CPT-Q4_K_M.gguf -p "Türkiye'de yenilenebilir enerji kaynaklarının önemi nedir?" -n 256
vngrs-ai/vngrs-web-corpus)Qwen/Qwen3.8-27B)