Slava Qwen3 14B Serbian 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 25 quants, from 0.0 GB to 12.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Slava Qwen3 14B Serbian – a fine‑tuned Qwen3 model for Serbian NLP tasks
Slava is a 14.8‑billion‑parameter Qwen3 model fully fine‑tuned for Serbian. It supports grammar correction, Serbian‑to‑English translation, summarization, sentiment analysis and aspect‑based sentiment analysis. The model is released under CC BY‑NC‑SA 4.0 for non‑commercial research use.
Good at
- Serbian grammar correction
- Serbian‑to‑English translation
- Sentiment analysis
Limits
- Non‑commercial license
- No vision or multimodal support
- Requires a Serbian system instruction
Best for
- Academic research on Serbian NLP
- Prototype Serbian language applications
- Non‑commercial educational demos
Who it’s for. Researchers and developers working on Serbian natural language processing who need a dedicated instruction‑style model. The model is suitable for academic projects, prototypes, and educational tools, but not for commercial deployment or safety‑critical systems.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 3.6 GB | 5.4 GB | Fits | Get file → | |
| IQ1_M | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ2_XXS | 4.3 GB | 6.1 GB | Fits | Get file → | |
| IQ2_XS | 4.7 GB | 6.5 GB | Fits | Get file → | |
| IQ2_S | 5.0 GB | 6.8 GB | Fits | Get file → | |
| IQ2_M | 5.3 GB | 7.2 GB | Fits | Get file → | |
| Q2_K_S | 5.4 GB | 7.2 GB | Tight | Get file → | |
| Q2_K | 5.8 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 5.9 GB | 7.8 GB | Tight | Get file → | |
| IQ3_XS | 6.4 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_S | 6.7 GB | 8.5 GB | Too big | Get file → | |
| IQ3_S | 6.7 GB | 8.5 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.3 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_L | 7.9 GB | 9.7 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 10.0 GB | Too big | Get file → | |
| IQ4_NL | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q4_0 | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 9.0 GB | 10.8 GB | Too big | Get file → | |
| Q4_1 | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_S | 10.3 GB | 12.1 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 12.4 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.0 GB | Too big | Get file → |
For 8 GB VRAM, use the IQ1_S quant (file size 3.58 GB, estimated 5.4 GB memory). If 12 GB VRAM is available, the Q4_K_M quant (9 GB, 10.8 GB memory) offers a good balance of size and performance. For larger GPUs, the Q5_K_M quant (10.51 GB, 12.4 GB memory) provides higher quality.
What GPU do you need for Slava Qwen3 14B Serbian?
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 the main file (0.0 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (3.8 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (5.9 GB file, about 7.8 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 Q6_K (12.1 GB file, about 14.0 GB in use).
Which Slava Qwen3 14B Serbian quant should you choose?
Q4_K_M is the usual starting point for Slava Qwen3 14B Serbian: it balances file size and quality well. Here it is a 9.0 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Slava Qwen3 14B Serbian
How much VRAM does Slava Qwen3 14B Serbian 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 Slava Qwen3 14B Serbian on an 8 GB GPU?
Yes, with IQ3_XXS: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Slava Qwen3 14B Serbian GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.6 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 5.0 GB and 19 more.
What context length does Slava Qwen3 14B Serbian 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 Slava Qwen3 14B Serbian GGUF?
The files are on Hugging Face in the mradermacher/Slava-Qwen3-14B-Serbian-i1-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 Slava Qwen3 14B Serbian use?
Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Slava on 8 GB VRAM?
Yes, the IQ1_S quant (3.58 GB) requires about 5.4 GB of VRAM at 8 k context, which fits within 8 GB.
Is Slava suitable for commercial products?
No. The CC BY‑NC‑SA 4.0 license restricts commercial use; it is intended for research and non‑commercial projects.
Does Slava support vision or multimodal inputs?
No. The model is purely text‑based and does not include vision or multimodal capabilities.