SA

Sailor-4B-Chat

SailorGGUF by mradermacherUpdated 2024-07-08
Download on Hugging Face
Parameters3.95B
Context32K
Layers40
Architectureqwen2
Smallest quant1.6 GB
Quick answer

Sailor-4B-Chat needs about 6.3 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 1.6 GB (Q2_K) to 7.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.

Sailor‑4B‑Chat – 3.95B parameter Qwen2 chat model for SEA languages

Sailor‑4B‑Chat is a 3.95B parameter Qwen2 model fine‑tuned for instruction following. It supports 32768 context tokens and is released under Apache‑2.0. The model is optimized for Indonesian, Thai, Vietnamese, Malay, and Lao.

Good at

  • Instruction‑tuned chat
  • SEA language understanding
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license

Best for

  • Chatbots in SEA languages
  • Content generation for regional apps
  • Local LLM deployment

Who it’s for. Developers building chat or content tools that need strong support for Southeast Asian languages. Researchers wanting a lightweight, instruction‑tuned model for local deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.6 GB 5.5 GB
Fits Get file →
IQ3_XS1.8 GB 5.6 GB
Fits Get file →
IQ3_S1.9 GB 5.7 GB
Fits Get file →
Q3_K_S1.9 GB 5.7 GB
Fits Get file →
IQ3_M1.9 GB 5.8 GB
Fits Get file →
Q3_K_M2.0 GB 5.9 GB
Fits Get file →
Q3_K_L2.2 GB 6.0 GB
Fits Get file →
IQ4_XS2.2 GB 6.1 GB
Fits Get file →
Q4_K_S2.3 GB 6.2 GB
Fits Get file →
Q4_K_M2.5 GB 6.3 GB
Fits Get file →
Q5_K_S2.8 GB 6.6 GB
Fits Get file →
Q5_K_M2.8 GB 6.7 GB
Fits Get file →
Q6_K3.2 GB 7.1 GB
Fits Get file →
Q8_04.2 GB 8.1 GB
Too big Get file →
F167.9 GB 11.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.46 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q5_K_M (2.84 GB, 6.7 GB memory) or Q6_K (3.25 GB, 7.1 GB memory). Larger VRAM allows Q8_0 (4.2 GB, 8.1 GB memory).

What GPU do you need for Sailor-4B-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: the best quant that fits is Q3_K_L (2.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.9 GB file, about 11.8 GB in use).

Which Sailor-4B-Chat quant should you choose?

Q4_K_M is the usual starting point for Sailor-4B-Chat: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.2 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 1.6 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
Parameters3.95B
Layers40
Trained context32,768 tokens
KV cache (fp16)400 KB per token

Source

Quantized bymradermacher
FamilySailor
Licenseapache-2.0
Downloads (HF)814
Last updated2024-07-08

Frequently asked questions about Sailor-4B-Chat

How much VRAM does Sailor-4B-Chat need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 2.5 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-4B-Chat on an 8 GB GPU?

Yes, with Q6_K: the 3.2 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sailor-4B-Chat GGUF?

It depends on the quant: Q2_K is 1.6 GB, IQ3_XS is 1.8 GB, IQ3_S is 1.9 GB, Q3_K_S is 1.9 GB, IQ3_M is 1.9 GB, Q3_K_M is 2.0 GB and 9 more.

What context length does Sailor-4B-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 3.4 GB at 8K and 13.4 GB at 32K.

Where can I download Sailor-4B-Chat GGUF?

The files are on Hugging Face in the mradermacher/Sailor-4B-Chat-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-4B-Chat 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‑4B‑Chat on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 6.3 GB of VRAM at 8k context, which fits within 8 GB.

Does Sailor‑4B‑Chat support image input?

No, the model has no vision capabilities.

What license applies to this model?

It is distributed under Apache‑2.0 and may be used for research and commercial purposes.

Other GGUFs of Sailor-4B-Chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sailor models

All Sailor →

Other small models

All small models →