Yi Coder 9B Chat needs about 4.4 GB of memory at IQ2_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.0 GB (IQ1_S) to 17.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Yi Coder 9B Chat is a 8.83B-parameter Coder model in GGUF format, quantized by CISCai. Its trained context length is 128K tokens. The repository has 12 quant files, from 2.0 GB (IQ1_S) to 17.7 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.0 GB | 3.3 GB | Fits | Get file → | |
| IQ1_M | 2.2 GB | 3.5 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 3.8 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.0 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.2 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XXS | 3.5 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.0 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.2 GB | Fits | Get file → | |
| IQ3_M | 4.1 GB | 5.4 GB | Fits | Get file → | |
| IQ4_XS | 4.8 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 17.7 GB (2 parts) | 19.0 GB | Too big | Get file → |
What GPU do you need for Yi Coder 9B 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: the best quant that fits is IQ2_XS (2.7 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.1 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_XS (4.8 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (4.8 GB file, about 6.1 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (4.8 GB file, about 6.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.7 GB file, about 19.0 GB in use).
Which Yi Coder 9B Chat quant should you choose?
IQ2_M (3.1 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 2.0 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 Yi Coder 9B Chat
How much VRAM does Yi Coder 9B Chat need?
About 4.4 GB at IQ2_M with an 8K context window. That is the 3.1 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 Yi Coder 9B Chat on an 8 GB GPU?
Yes, with IQ4_XS: the 4.8 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Yi Coder 9B Chat GGUF?
It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB, IQ2_M is 3.1 GB and 6 more.
What context length does Yi Coder 9B Chat support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Yi Coder 9B Chat GGUF?
The files are on Hugging Face in the CISCai/Yi-Coder-9B-Chat-SOTA-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 Yi Coder 9B 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.