Sailor-14B-Chat needs about 16.4 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 4.5 GB (IQ1_S) to 15.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.
Sailor‑14B‑Chat, a 14.2B‑parameter Qwen2 model for SEA languages
Sailor‑14B‑Chat is a 14.2B‑parameter Qwen2 model focused on South‑East Asian languages. It supports a 32,768‑token context window and is available in multiple GGUF quantizations. The model is licensed under an other license.
Good at
- Large context handling
- SEA language support
- Chat‑style generation
Limits
- No vision support
- License not standard
- Requires 8‑k context for memory estimates
Best for
- Chatbots in Indonesian, Thai, Vietnamese, Malay, Lao
- Text generation for SEA content
- Fine‑tuning on regional corpora
Who it’s for. Developers building chat or content generation tools for South‑East Asian markets. Researchers needing a large‑context model for regional languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.5 GB | 11.7 GB | Too big | Get file → | |
| IQ1_M | 4.7 GB | 11.9 GB | Too big | Get file → | |
| IQ2_XXS | 5.0 GB | 12.2 GB | Too big | Get file → | |
| IQ2_XS | 5.3 GB | 12.5 GB | Too big | Get file → | |
| IQ2_S | 5.6 GB | 12.8 GB | Too big | Get file → | |
| Q2_K_S | 5.7 GB | 13.0 GB | Too big | Get file → | |
| IQ2_M | 5.8 GB | 13.0 GB | Too big | Get file → | |
| Q2_K | 5.9 GB | 13.1 GB | Too big | Get file → | |
| IQ3_XXS | 6.1 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XS | 6.5 GB | 13.7 GB | Too big | Get file → | |
| IQ3_S | 6.8 GB | 14.0 GB | Too big | Get file → | |
| Q3_K_S | 6.8 GB | 14.0 GB | Too big | Get file → | |
| IQ3_M | 7.1 GB | 14.3 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 15.1 GB | Too big | Get file → | |
| IQ4_XS | 7.8 GB | 15.1 GB | Too big | Get file → | |
| IQ4_NL | 8.2 GB | 15.4 GB | Too big | Get file → | |
| Q4_0 | 8.2 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 15.8 GB | Too big | Get file → | |
| Q4_1 | 9.0 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_M | 9.2 GB | 16.4 GB | Too big | Get file → | |
| Q5_0 | 9.9 GB | 17.1 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 17.2 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 17.7 GB | Too big | Get file → | |
| Q5_1 | 10.7 GB | 17.9 GB | Too big | Get file → | |
| Q6_K | 12.3 GB | 19.5 GB | Too big | Get file → | |
| Q8_0 | 15.1 GB | 22.3 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (4.5 GB, 11.7 GB memory at 8k context). For 12‑GB VRAM, use Q2_K (5.91 GB, 13.1 GB memory). For 16‑GB VRAM, Q4_K_M (9.19 GB, 16.4 GB memory) offers a balance between size and performance. Estimates are approximate.
What GPU do you need for Sailor-14B-Chat?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ1_M (4.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (8.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 22.3 GB in use).
Which Sailor-14B-Chat quant should you choose?
Q4_K_M is the usual starting point for Sailor-14B-Chat: it balances file size and quality well. Here it is a 9.2 GB file.
The Q8_0 file is 15.1 GB, about 1.6 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 IQ1_S at 4.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sailor-14B-Chat
How much VRAM does Sailor-14B-Chat need?
About 16.4 GB at Q4_K_M with an 8K context window. That is the 9.2 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 Sailor-14B-Chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Sailor-14B-Chat GGUF?
It depends on the quant: IQ1_S is 4.5 GB, IQ1_M is 4.7 GB, IQ2_XXS is 5.0 GB, IQ2_XS is 5.3 GB, IQ2_S is 5.6 GB, Q2_K_S is 5.7 GB and 21 more.
What context length does Sailor-14B-Chat support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.
Where can I download Sailor-14B-Chat GGUF?
The files are on Hugging Face in the duyntnet/Sailor-14B-Chat-imatrix-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 Sailor-14B-Chat use?
Hugging Face lists the license as other. 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 Sailor‑14B‑Chat on 8 GB VRAM?
Yes, the IQ1_S quantization is 4.5 GB and requires about 11.7 GB memory at 8k context, which fits within 8 GB VRAM with efficient batching.
Does Sailor‑14B‑Chat support image inputs?
No, the model does not have vision capabilities.
What languages does Sailor‑14B‑Chat handle well?
It is tailored for Indonesian, Thai, Vietnamese, Malay, and Lao.