Test Model 22 needs about 67.5 GB of memory at Q4_K (a 63.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 16.1 GB.
Test Model 22 is a 105B-parameter Test model in GGUF format, quantized by bruhzair. Its trained context length is 128K tokens. The repository has 1 quant file, from 63.0 GB (Q4_K) to 63.0 GB (Q4_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 63.0 GB (2 parts) | 67.5 GB | Too big | Get file → |
What GPU do you need for Test Model 22?
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 Test Model 22 quant should you choose?
Q4_K (63.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Test Model 22
How much VRAM does Test Model 22 need?
About 67.5 GB at Q4_K with an 8K context window. That is the 63.0 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 Test Model 22 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 67.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Test Model 22 GGUF?
It depends on the quant: Q4_K is 63.0 GB.
What context length does Test Model 22 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.
Where can I download Test Model 22 GGUF?
The files are on Hugging Face in the bruhzair/Test-Model-22-105B-Q4_K repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.