Sailor-1.8B needs about 3.3 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.8 GB (Q2_K) to 3.7 GB (F16).
Sailor‑1.8B, a 1.84B‑parameter Qwen2 model for Southeast Asian languages
Sailor‑1.8B is a 1.84B‑parameter Qwen2 model trained on Southeast Asian text. It supports 8192‑token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.
Good at
- SEA language generation
- Instruction following
- Multilingual text tasks
Limits
- No vision support
- Requires 8192‑token context
- Apache‑2.0 license
Best for
- Chatbots in Indonesian
- Content creation in Thai
- Localization in Vietnamese
Who it’s for. Developers building local LLM applications for Southeast Asia. Researchers needing a lightweight SEA‑focused model. Enterprises wanting an open‑source model with no commercial restrictions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XS | 0.9 GB | 3.0 GB | Fits | Get file → | |
| IQ3_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| IQ3_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_L | 1.1 GB | 3.2 GB | Fits | Get file → | |
| IQ4_XS | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_S | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 4.1 GB | Fits | Get file → | |
| F16 | 3.7 GB | 5.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.22 GB file, ~3.3 GB memory). For 4 GB VRAM, use Q3_K_S (0.95 GB file, ~3.1 GB memory). For 2 GB VRAM, use Q2_K (0.85 GB file, ~3 GB memory). Estimates are approximate.
What GPU do you need for Sailor-1.8B?
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 Q6_K (1.6 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).
Which Sailor-1.8B quant should you choose?
Q4_K_M is the usual starting point for Sailor-1.8B: it balances file size and quality well. Here it is a 1.2 GB file.
The Q8_0 file is 2.0 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 Q2_K at 0.8 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-1.8B
How much VRAM does Sailor-1.8B need?
About 3.3 GB at Q4_K_M with an 8K context window. That is the 1.2 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-1.8B on an 8 GB GPU?
Yes, with F16: the 3.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sailor-1.8B GGUF?
It depends on the quant: Q2_K is 0.8 GB, IQ3_XS is 0.9 GB, IQ3_S is 1.0 GB, Q3_K_S is 1.0 GB, IQ3_M is 1.0 GB, Q3_K_M is 1.0 GB and 9 more.
What context length does Sailor-1.8B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download Sailor-1.8B GGUF?
The files are on Hugging Face in the mradermacher/Sailor-1.8B-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-1.8B 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 Sailor‑1.8B on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with about 3.3 GB memory usage.
Does Sailor‑1.8B support vision tasks?
No, the model is purely text‑based and has no vision capability.
What license applies to Sailor‑1.8B?
The model is distributed under Apache‑2.0, allowing both research and commercial use.