sail.Sailor2 20B Chat needs about 14.3 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 7.4 GB (Q2_K) to 20.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
sail.Sailor2 20B Chat is a 19.2B-parameter Sailor model in GGUF format, quantized by DevQuasar-5. Its trained context length is 32K tokens. The repository has 6 quant files, from 7.4 GB (Q2_K) to 20.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.4 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_M | 9.5 GB | 12.1 GB | Too big | Get file → | |
| Q4_K_M | 11.6 GB | 14.3 GB | Too big | Get file → | |
| Q5_K_M | 13.6 GB | 16.3 GB | Too big | Get file → | |
| Q6_K | 15.7 GB | 18.4 GB | Too big | Get file → | |
| Q8_0 | 20.4 GB | 23.0 GB | Too big | Get file → |
What GPU do you need for sail.Sailor2 20B 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 Q2_K (7.4 GB file, about 10.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (11.6 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (20.4 GB file, about 23.0 GB in use).
Which sail.Sailor2 20B Chat quant should you choose?
Q4_K_M is the usual starting point for sail.Sailor2 20B Chat: it balances file size and quality well. Here it is a 11.6 GB file.
The Q8_0 file is 20.4 GB, about 1.8 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 7.4 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 sail.Sailor2 20B Chat
How much VRAM does sail.Sailor2 20B Chat need?
About 14.3 GB at Q4_K_M with an 8K context window. That is the 11.6 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 sail.Sailor2 20B Chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of sail.Sailor2 20B Chat GGUF?
It depends on the quant: Q2_K is 7.4 GB, Q3_K_M is 9.5 GB, Q4_K_M is 11.6 GB, Q5_K_M is 13.6 GB, Q6_K is 15.7 GB, Q8_0 is 20.4 GB.
What context length does sail.Sailor2 20B 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 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download sail.Sailor2 20B Chat GGUF?
The files are on Hugging Face in the DevQuasar-5/sail.Sailor2-20B-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 sail.Sailor2 20B 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.