SA

Sailor-0.5B

SailorGGUF by mradermacherUpdated 2024-07-08
Download on Hugging Face
Parameters620M
Context32K
Layers24
Architectureqwen2
Smallest quant0.3 GB
Quick answer

Sailor-0.5B needs about 1.7 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.3 GB (Q2_K) to 1.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Sailor‑0.5B – a 0.62B‑parameter Qwen2 model for Southeast Asian languages

Sailor‑0.5B is a 0.62B‑parameter Qwen2 model focused on Indonesian, Thai, Vietnamese, Malay, and Lao. It is trained on 400 B tokens and supports a 32 768‑token context window. The model is released under Apache‑2.0.

Good at

  • SEA language understanding
  • Instruction‑tuned text generation
  • Low‑resource deployment

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • No explicit language list

Best for

  • Chatbots in SEA languages
  • Content generation for local media
  • Educational tools for regional languages

Who it’s for. Developers building local language applications who need a lightweight, instruction‑tuned model. Researchers exploring Southeast Asian NLP can use it as a base for further fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.6 GB
Fits Get file →
IQ3_XS0.3 GB 1.6 GB
Fits Get file →
IQ3_S0.3 GB 1.6 GB
Fits Get file →
Q3_K_S0.3 GB 1.6 GB
Fits Get file →
IQ3_M0.3 GB 1.6 GB
Fits Get file →
Q3_K_M0.3 GB 1.7 GB
Fits Get file →
Q3_K_L0.4 GB 1.7 GB
Fits Get file →
IQ4_XS0.4 GB 1.7 GB
Fits Get file →
Q4_K_S0.4 GB 1.7 GB
Fits Get file →
Q4_K_M0.4 GB 1.7 GB
Fits Get file →
Q5_K_S0.5 GB 1.8 GB
Fits Get file →
Q5_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.5 GB 1.8 GB
Fits Get file →
Q8_00.7 GB 2.0 GB
Fits Get file →
F161.2 GB 2.6 GB
Fits Get file →

For 8 GB VRAM use Q4_K or Q5_K_S (file size 0.4 GB, ~1.7 GB memory). For 12 GB VRAM Q6_K (0.51 GB, ~1.8 GB). For 16 GB VRAM Q8_0 (0.66 GB, ~2 GB).

What GPU do you need for Sailor-0.5B?

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 F16 (1.2 GB file, about 2.6 GB in use).

Which Sailor-0.5B quant should you choose?

Q4_K_M is the usual starting point for Sailor-0.5B: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.7 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 0.3 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

Architectureqwen2
Parameters620M
Layers24
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilySailor
Licenseapache-2.0
Downloads (HF)1,527
Last updated2024-07-08

Frequently asked questions about Sailor-0.5B

How much VRAM does Sailor-0.5B need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.4 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-0.5B on an 8 GB GPU?

Yes, with F16: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sailor-0.5B GGUF?

It depends on the quant: Q2_K is 0.3 GB, IQ3_XS is 0.3 GB, IQ3_S is 0.3 GB, Q3_K_S is 0.3 GB, IQ3_M is 0.3 GB, Q3_K_M is 0.3 GB and 9 more.

What context length does Sailor-0.5B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Sailor-0.5B GGUF?

The files are on Hugging Face in the mradermacher/Sailor-0.5B-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-0.5B 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‑0.5B on 8 GB VRAM?

Yes, use Q4_K or Q5_K_S quantizations; memory usage is about 1.7 GB at 8 k context.

Does Sailor‑0.5B support vision tasks?

No, the model is purely text‑based and has no vision capabilities.

What license applies to Sailor‑0.5B?

Apache‑2.0, allowing research and commercial use under the Qwen license.

Other GGUFs of Sailor-0.5B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sailor models

All Sailor →

Other tiny models

All tiny models →