SU

Sungur 14B GGUF

SungurGGUF by suayptalhaUpdated 2025-10-01
Download on Hugging Face
Parameters14.8B
Context40K
Layers40
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Sungur 14B GGUF needs about 10.8 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 18 quants, from 0.0 GB (Q5_K_S) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Sungur 14B GGUF – Turkish‑specialized reasoning model

Sungur 14B GGUF is a 14.8B parameter model based on Qwen3. It was fine‑tuned with a Turkish reasoning dataset and supports advanced reasoning and tool use. The model is available in multiple quantizations for different memory budgets.

Good at

  • Turkish reasoning
  • Tool‑enabled dialogue
  • Logical text generation

Limits

  • No vision support
  • Requires 8.0k context for full capability
  • Apache‑2.0 license

Best for

  • Educational tutoring in Turkish
  • Domain‑specific problem solving
  • Analytical dialogue

Who it’s for. Developers building Turkish language applications that need strong reasoning and tool integration. Researchers exploring Turkish NLP can use the model for fine‑tuning and evaluation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S0.0 GB 1.8 GB
Fits Get file →
Q6_K0.0 GB 1.8 GB
Fits Get file →
Q5_11.7 GB 3.5 GB
Fits Get file →
Q2_K5.8 GB 7.6 GB
Tight Get file →
Q3_K_S6.7 GB 8.5 GB
Too big Get file →
Q3_K_M7.3 GB 9.2 GB
Too big Get file →
Q3_K_L7.9 GB 9.7 GB
Too big Get file →
Q4_08.5 GB 10.4 GB
Too big Get file →
Q4_K_S8.6 GB 10.4 GB
Too big Get file →
Q4_K9.0 GB 10.8 GB
Too big Get file →
Q4_K_M9.0 GB 10.8 GB
Too big Get file →
Q4_19.4 GB 11.2 GB
Too big Get file →
Q5_010.3 GB 12.1 GB
Too big Get file →
Q5_K10.5 GB 12.4 GB
Too big Get file →
Q5_K_M10.5 GB 12.4 GB
Too big Get file →
Q8_015.7 GB 17.5 GB
Too big Get file →
BF1629.5 GB 31.4 GB
Too big Get file →
F1629.5 GB 31.4 GB
Too big Get file →

For 8 GB VRAM use Q5_K_S or Q6_K, each needs about 1.8 GB at 8 k context. With 16 GB VRAM Q5_1 or Q2_K are suitable, requiring 3.5 GB or 7.6 GB respectively. For 32 GB VRAM, Q4_K_M or Q4_K provide 10.8 GB usage, while Q8_0 needs 17.5 GB.

What GPU do you need for Sungur 14B GGUF?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q5_1 (1.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_1 (1.7 GB file, about 3.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.4 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K (10.5 GB file, about 12.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.5 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.4 GB in use).

Which Sungur 14B GGUF quant should you choose?

Q4_K_M is the usual starting point for Sungur 14B GGUF: it balances file size and quality well. Here it is a 9.0 GB file.

The Q8_0 file is 15.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q5_K_S at 0.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters14.8B
Layers40
Trained context40,960 tokens
KV cache (fp16)160 KB per token

Source

Quantized bysuayptalha
FamilySungur
Licenseapache-2.0
Downloads (HF)832
Last updated2025-10-01

Frequently asked questions about Sungur 14B GGUF

How much VRAM does Sungur 14B GGUF need?

About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Sungur 14B GGUF on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sungur 14B GGUF GGUF?

It depends on the quant: Q5_K_S is 0.0 GB, Q6_K is 0.0 GB, Q5_1 is 1.7 GB, Q2_K is 5.8 GB, Q3_K_S is 6.7 GB, Q3_K_M is 7.3 GB and 12 more.

What context length does Sungur 14B GGUF support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Sungur 14B GGUF GGUF?

The files are on Hugging Face in the suayptalha/Sungur-14B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Sungur 14B GGUF use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Sungur 14B on 8 GB VRAM?

Yes, use Q5_K_S or Q6_K quantizations, each estimated at 1.8 GB memory at 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Sungur-14B

Similar models

Browse all →

More from suayptalha

All by suayptalha →

More Sungur models

All Sungur →

Other medium models

All medium models →