LT Upscale needs about 82.1 GB of memory at Q4_K_M (a 72.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 57.0 GB (Q3_K_M) to 99.0 GB (Q6_K).
LT Upscale is a 110B-parameter Upscale model in GGUF format, quantized by Gandalf69. Its trained context length is 128K tokens. The repository has 5 quant files, from 57.0 GB (Q3_K_M) to 99.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 57.0 GB (6 parts) | 64.4 GB | Too big | Get file → | |
| Q4_K_M | 72.9 GB (8 parts) | 82.1 GB | Too big | Get file → | |
| Q5_K_S | 78.3 GB (8 parts) | 88.2 GB | Too big | Get file → | |
| Q5_K_M | 83.4 GB (9 parts) | 93.9 GB | Too big | Get file → | |
| Q6_K | 99.0 GB (11 parts) | 111.4 GB | Too big | Get file → |
What GPU do you need for LT Upscale?
These figures add the file size, an fp16 KV cache at an 8K context window 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 LT Upscale quant should you choose?
Q4_K_M is the usual starting point for LT Upscale: it balances file size and quality well. Here it is a 72.9 GB file.
If memory is tight, the smallest file is Q3_K_M at 57.0 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 LT Upscale
How much VRAM does LT Upscale need?
About 82.1 GB at Q4_K_M with an 8K context window. That is the 72.9 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 LT Upscale on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 64.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LT Upscale GGUF?
It depends on the quant: Q3_K_M is 57.0 GB, Q4_K_M is 72.9 GB, Q5_K_S is 78.3 GB, Q5_K_M is 83.4 GB, Q6_K is 99.0 GB.
What context length does LT Upscale support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download LT Upscale GGUF?
The files are on Hugging Face in the Gandalf69/LT-Upscale repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.