Yi Ko 34B needs about 39.3 GB of memory at Q8_0 (a 36.8 GB file) with an 8K context window, so it fits on a 48 GB GPU.
Yi Ko 34B is a 34.6B-parameter model in GGUF format, quantized by skraparks. Its trained context length is 2K tokens. The repository has 1 quant file, from 36.8 GB (Q8_0) to 36.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 36.8 GB | 37.8 GB | Too big | Get file → |
What GPU do you need for Yi Ko 34B?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q8_0 (36.8 GB file, about 39.3 GB in use).
Which Yi Ko 34B quant should you choose?
Q8_0 (36.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Yi Ko 34B
How much VRAM does Yi Ko 34B need?
About 39.3 GB at Q8_0 with an 8K context window. That is the 36.8 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 Yi Ko 34B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 39.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Yi Ko 34B GGUF?
It depends on the quant: Q8_0 is 36.8 GB.
What context length does Yi Ko 34B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.0 GB at 8K and 0.5 GB at 2K.
Where can I download Yi Ko 34B GGUF?
The files are on Hugging Face in the skraparks/Yi-Ko-34B-Q8_0-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 Ko 34B 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.