Hy3 REAP 200B 21B needs about 125.6 GB of memory at Q4_K_M (a 122.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 67.0 GB (IQ2_M) to 143.5 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.9 GB.
Hy3 REAP 200B 21B is a 202B-parameter Reap model in GGUF format, quantized by OpenMOSE. Its trained context length is 256K tokens. The repository has 5 quant files, from 67.0 GB (IQ2_M) to 143.5 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 67.0 GB (4 parts) | 70.3 GB | Too big | Get file → | |
| IQ3_XXS | 78.6 GB (4 parts) | 81.8 GB | Too big | Get file → | |
| IQ4_XS | 108.3 GB (6 parts) | 111.5 GB | Too big | Get file → | |
| Q4_K_M | 122.4 GB (7 parts) | 125.6 GB | Too big | Get file → | |
| Q5_K_M | 143.5 GB (8 parts) | 146.7 GB | Too big | Get file → |
What GPU do you need for Hy3 REAP 200B 21B?
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 REAP 200B 21B quant should you choose?
Q4_K_M is the usual starting point for Hy3 REAP 200B 21B: it balances file size and quality well. Here it is a 122.4 GB file.
If memory is tight, the smallest file is IQ2_M at 67.0 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 Hy3 REAP 200B 21B
How much VRAM does Hy3 REAP 200B 21B need?
About 125.6 GB at Q4_K_M with an 8K context window. That is the 122.4 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 REAP 200B 21B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 70.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hy3 REAP 200B 21B GGUF?
It depends on the quant: IQ2_M is 67.0 GB, IQ3_XXS is 78.6 GB, IQ4_XS is 108.3 GB, Q4_K_M is 122.4 GB, Q5_K_M is 143.5 GB.
What context length does Hy3 REAP 200B 21B 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 REAP 200B 21B GGUF?
The files are on Hugging Face in the OpenMOSE/Hy3-REAP-200B-21B-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 REAP 200B 21B 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.