Hy3 needs about 187.9 GB of memory at Q4_K_M (a 184.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 0.6 GB to 184.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.9 GB.
Hy3 is a 299B-parameter model in GGUF format, quantized by AtomicChat. Its trained context length is 256K tokens. The repository has 3 quant files, from 0.6 GB to 184.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.6 GB | 3.8 GB | Fits | Get file → | |
| IQ1_M | 91.8 GB | 95.0 GB | Too big | Get file → | |
| Q4_K_M | 184.7 GB | 187.9 GB | Too big | Get file → |
What GPU do you need for Hy3?
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 the main file (0.6 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.6 GB file, about 3.8 GB in use).
Which Hy3 quant should you choose?
Q4_K_M is the usual starting point for Hy3: it balances file size and quality well. Here it is a 184.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.6 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy3
How much VRAM does Hy3 need?
About 187.9 GB at Q4_K_M with an 8K context window. That is the 184.7 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 Hy3 on an 8 GB GPU?
Yes, with the smaller files: the 0.6 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hy3 GGUF?
It depends on the quant: file is 0.6 GB, IQ1_M is 91.8 GB, Q4_K_M is 184.7 GB.
What context length does Hy3 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 10.9 GB at 32K.
Where can I download Hy3 GGUF?
The files are on Hugging Face in the AtomicChat/Hy3-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 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.