kyujinpy PlatYi 34B Q needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 1.5 GB (IQ3_XS) to 36.5 GB (Q8_0).
kyujinpy PlatYi 34B Q is a 34.4B-parameter Kyujinpy model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 22 quant files, from 1.5 GB (IQ3_XS) to 36.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 1.5 GB | 3.0 GB | Fits | Get file → | |
| Q4_K | 9.6 GB | 11.1 GB | Too big | Get file → | |
| Q2_K | 12.8 GB | 14.3 GB | Too big | Get file → | |
| IQ4_NL | 14.5 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_S | 15.0 GB | 16.5 GB | Too big | Get file → | |
| IQ3_S | 15.0 GB | 16.5 GB | Too big | Get file → | |
| IQ3_M | 15.6 GB | 17.1 GB | Too big | Get file → | |
| Q3_K | 16.7 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_M | 16.7 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_L | 18.1 GB | 19.6 GB | Too big | Get file → | |
| IQ4_XS | 18.6 GB | 20.1 GB | Too big | Get file → | |
| Q4_0 | 19.5 GB | 21.0 GB | Too big | Get file → | |
| Q4_K_S | 19.6 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 20.7 GB | 22.2 GB | Too big | Get file → | |
| Q4_1 | 21.6 GB | 23.1 GB | Too big | Get file → | |
| Q5_0 | 23.7 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_S | 23.7 GB | 25.2 GB | Too big | Get file → | |
| Q5_K | 24.3 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_M | 24.3 GB | 25.8 GB | Too big | Get file → | |
| Q5_1 | 25.8 GB | 27.3 GB | Too big | Get file → | |
| Q6_K | 28.2 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.5 GB | 38.0 GB | Too big | Get file → |
What GPU do you need for kyujinpy PlatYi 34B Q?
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 IQ3_XS (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XS (1.5 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (1.5 GB file, about 4.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (1.5 GB file, about 4.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (12.8 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).
Which kyujinpy PlatYi 34B Q quant should you choose?
Q4_K_M is the usual starting point for kyujinpy PlatYi 34B Q: it balances file size and quality well. Here it is a 20.7 GB file.
The Q8_0 file is 36.5 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 IQ3_XS at 1.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kyujinpy PlatYi 34B Q
How much VRAM does kyujinpy PlatYi 34B Q need?
About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 kyujinpy PlatYi 34B Q on an 8 GB GPU?
Yes, with IQ3_XS: the 1.5 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kyujinpy PlatYi 34B Q GGUF?
It depends on the quant: IQ3_XS is 1.5 GB, Q4_K is 9.6 GB, Q2_K is 12.8 GB, IQ4_NL is 14.5 GB, Q3_K_S is 15.0 GB, IQ3_S is 15.0 GB and 16 more.
What context length does kyujinpy PlatYi 34B Q support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.
Where can I download kyujinpy PlatYi 34B Q GGUF?
The files are on Hugging Face in the RichardErkhov/kyujinpy_-_PlatYi-34B-Q-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 kyujinpy PlatYi 34B Q use?
Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.