SA

Sailor-7B

SailorGGUF by mradermacherUpdated 2024-07-08
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen2
Smallest quant3.1 GB
Quick answer

Sailor-7B needs about 9.6 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.1 GB (Q2_K) to 15.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Sailor-7B: 7.72B parameter Qwen2 model for Southeast Asian languages

Sailor-7B is a 7.72B parameter Qwen2 model fine‑tuned for Southeast Asian languages. It supports a 32,768 token context window and is distributed under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following in SEA languages
  • Large context handling
  • Low‑memory inference

Limits

  • No vision support
  • Requires 8,000 token context for memory estimates
  • Apache‑2.0 license with Qwen license conditions

Best for

  • Chatbots in Indonesian, Thai, Vietnamese, Malay, Lao
  • Text generation for SEA language content
  • Fine‑tuning for regional applications

Who it’s for. Researchers and developers building applications that need robust language understanding in Southeast Asian languages. The model is suitable for both academic and commercial use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 7.9 GB
Tight Get file →
IQ3_XS3.4 GB 8.2 GB
Too big Get file →
IQ3_S3.6 GB 8.4 GB
Too big Get file →
Q3_K_S3.6 GB 8.4 GB
Too big Get file →
IQ3_M3.7 GB 8.5 GB
Too big Get file →
Q3_K_M3.9 GB 8.7 GB
Too big Get file →
Q3_K_L4.2 GB 9.0 GB
Too big Get file →
IQ4_XS4.3 GB 9.1 GB
Too big Get file →
Q4_K_S4.5 GB 9.3 GB
Too big Get file →
Q4_K_M4.8 GB 9.6 GB
Too big Get file →
Q5_K_S5.4 GB 10.2 GB
Too big Get file →
Q5_K_M5.5 GB 10.3 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →
Q8_08.2 GB 13.0 GB
Too big Get file →
F1615.4 GB 20.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.77 GB, estimated 9.6 GB memory). For 12 GB VRAM, Q5_K_M (5.53 GB, 10.3 GB memory) is a good balance. For 16 GB VRAM, Q6_K (6.34 GB, 11.1 GB memory) offers higher quality.

What GPU do you need for Sailor-7B?

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: the best quant that fits is Q2_K (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 13.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.4 GB file, about 20.2 GB in use).

Which Sailor-7B quant should you choose?

Q4_K_M is the usual starting point for Sailor-7B: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.2 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 Q2_K at 3.1 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
Parameters7.72B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilySailor
Base modelsail/Sailor-7B
Licenseapache-2.0
Downloads (HF)994
Last updated2024-07-08

Frequently asked questions about Sailor-7B

How much VRAM does Sailor-7B need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 4.8 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-7B on an 8 GB GPU?

Yes, with Q2_K: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sailor-7B GGUF?

It depends on the quant: Q2_K is 3.1 GB, IQ3_XS is 3.4 GB, IQ3_S is 3.6 GB, Q3_K_S is 3.6 GB, IQ3_M is 3.7 GB, Q3_K_M is 3.9 GB and 9 more.

What context length does Sailor-7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Sailor-7B GGUF?

The files are on Hugging Face in the mradermacher/Sailor-7B-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-7B 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-7B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 9.6 GB of VRAM at 8,000 token context, which fits within 8 GB with some headroom.

Does Sailor-7B support vision tasks?

No, the model is purely text‑based and does not include vision capabilities.

What license applies to Sailor-7B?

It is released under Apache‑2.0, but users must also comply with the Qwen license for large‑scale deployment.

Other GGUFs of Sailor-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sailor models

All Sailor →

Other small models

All small models →