Hy3 128GB needs about 126.6 GB of memory at its main file (a 123.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 114.9 GB (BF16) to 127.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Hy3 128GB is a 295B-parameter model in GGUF format, quantized by Sciguy429. Its trained context length is 256K tokens. The repository has 4 quant files, from 114.9 GB (BF16) to 127.2 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 114.9 GB (5 parts) | 118.1 GB | Too big | Get file → | |
| — | 123.4 GB (5 parts) | 126.6 GB | Too big | Get file → | |
| — | 127.1 GB (6 parts) | 130.3 GB | Too big | Get file → | |
| — | 127.2 GB (5 parts) | 130.3 GB | Too big | Get file → |
What GPU do you need for Hy3 128GB?
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: no quant fits at an 8K context.
Which Hy3 128GB quant should you choose?
If memory is tight, the smallest file is BF16 at 114.9 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy3 128GB
How much VRAM does Hy3 128GB need?
About 126.6 GB at its main file with an 8K context window. That is the 123.4 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 Hy3 128GB on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 118.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hy3 128GB GGUF?
It depends on the quant: BF16 is 114.9 GB, file is 123.4 GB, file is 127.1 GB, file is 127.2 GB.
What context length does Hy3 128GB support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Hy3 128GB GGUF?
The files are on Hugging Face in the Sciguy429/Hy3-128GB-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 Hy3 128GB 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.