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 27 quants, from 4.5 GB (IQ1_S) to 20.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Sailor2 20B Chat – a 19.2B‑parameter multilingual chat model
Sailor2 20B Chat is a 19.2B‑parameter model based on the Qwen2 architecture. It supports 15 languages and is trained on 500B tokens. The model is available in multiple GGUF quantizations for llama.cpp and other inference clients.
Good at
- Multilingual chat
- Large context handling
- High token throughput
Limits
- Requires 8k context for estimates
- No vision support
- License is other
Best for
- Chatbots needing 15‑language support
- Research on multilingual LLMs
- Production use in SEA regions
Who it’s for. Developers building multilingual chat applications or researchers needing a large‑parameter model with broad language coverage. The model is suitable for environments that can accommodate the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.5 GB | 7.2 GB | Fits | Get file → | |
| IQ1_M | 4.9 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XXS | 5.5 GB | 8.1 GB | Too big | Get file → | |
| IQ2_XS | 6.0 GB | 8.7 GB | Too big | Get file → | |
| IQ2_S | 6.4 GB | 9.0 GB | Too big | Get file → | |
| IQ2_M | 6.8 GB | 9.5 GB | Too big | Get file → | |
| Q2_K_S | 6.9 GB | 9.5 GB | Too big | Get file → | |
| Q2_K | 7.4 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XXS | 7.6 GB | 10.3 GB | Too big | Get file → | |
| IQ3_XS | 8.2 GB | 10.8 GB | Too big | Get file → | |
| Q3_K_S | 8.6 GB | 11.2 GB | Too big | Get file → | |
| IQ3_S | 8.6 GB | 11.2 GB | Too big | Get file → | |
| IQ3_M | 8.9 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_M | 9.5 GB | 12.1 GB | Too big | Get file → | |
| Q3_K_L | 10.2 GB | 12.9 GB | Too big | Get file → | |
| IQ4_XS | 10.5 GB | 13.1 GB | Too big | Get file → | |
| Q4_0 | 11.0 GB | 13.7 GB | Too big | Get file → | |
| IQ4_NL | 11.0 GB | 13.7 GB | Too big | Get file → | |
| Q4_K_S | 11.1 GB | 13.7 GB | Too big | Get file → | |
| Q4_K_M | 11.6 GB | 14.3 GB | Too big | Get file → | |
| Q4_1 | 12.1 GB | 14.8 GB | Too big | Get file → | |
| Q5_K_S | 13.3 GB | 15.9 GB | Too big | Get file → | |
| Q5_0 | 13.3 GB | 16.0 GB | Too big | Get file → | |
| Q5_K_M | 13.6 GB | 16.3 GB | Too big | Get file → | |
| Q5_1 | 14.4 GB | 17.1 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 → |
For 8‑GB VRAM, use IQ1_S or IQ1_M. For 12‑GB VRAM, Q4_K_M or Q4_1 are suitable. For 16‑GB VRAM, Q5_K_M or Q5_1 provide a good balance of quality and memory usage. Estimates are approximate.
What GPU do you need for 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: the best quant that fits is IQ1_M (4.9 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_M (8.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_0 (13.3 GB file, about 16.0 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 Sailor2 20B Chat quant should you choose?
Q4_K_M is the usual starting point for 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 IQ1_S at 4.5 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 Sailor2 20B Chat
How much VRAM does 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 Sailor2 20B Chat on an 8 GB GPU?
Yes, with IQ1_M: the 4.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sailor2 20B Chat GGUF?
It depends on the quant: IQ1_S is 4.5 GB, IQ1_M is 4.9 GB, IQ2_XXS is 5.5 GB, IQ2_XS is 6.0 GB, IQ2_S is 6.4 GB, IQ2_M is 6.8 GB and 21 more.
What context length does 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 Sailor2 20B Chat GGUF?
The files are on Hugging Face in the duyntnet/Sailor2-20B-Chat-imatrix-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 Sailor2 20B Chat use?
Hugging Face lists the license as other. 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 Sailor2 20B Chat on 8 GB VRAM?
Yes, using the IQ1_S or IQ1_M quantizations, which estimate 7.2–7.5 GB at 8k context.
Does Sailor2 20B Chat support vision?
No, the model does not include vision capabilities.