L3.0 Upscale 1 needs about 8.8 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.3 GB (Q2_K) to 11.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.
L3.0 Upscale 1 is a 11.1B-parameter Upscale model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 11 quant files, from 4.3 GB (Q2_K) to 11.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.3 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_S | 5.0 GB | 7.0 GB | Fits | Get file → | |
| Q3_K_M | 5.5 GB | 7.5 GB | Tight | Get file → | |
| Q3_K_L | 5.9 GB | 8.0 GB | Tight | Get file → | |
| IQ4_XS | 6.1 GB | 8.2 GB | Too big | Get file → | |
| Q4_K_S | 6.4 GB | 8.5 GB | Too big | Get file → | |
| Q4_K_M | 6.7 GB | 8.8 GB | Too big | Get file → | |
| Q5_K_S | 7.7 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_M | 7.9 GB | 9.9 GB | Too big | Get file → | |
| Q6_K | 9.1 GB | 11.1 GB | Too big | Get file → | |
| Q8_0 | 11.8 GB | 13.8 GB | Too big | Get file → |
What GPU do you need for L3.0 Upscale 1?
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: the best quant that fits is Q3_K_L (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.1 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (11.8 GB file, about 13.8 GB in use).
Which L3.0 Upscale 1 quant should you choose?
Q4_K_M is the usual starting point for L3.0 Upscale 1: it balances file size and quality well. Here it is a 6.7 GB file.
The Q8_0 file is 11.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 4.3 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 L3.0 Upscale 1
How much VRAM does L3.0 Upscale 1 need?
About 8.8 GB at Q4_K_M with an 8K context window. That is the 6.7 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 L3.0 Upscale 1 on an 8 GB GPU?
Yes, with Q3_K_L: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of L3.0 Upscale 1 GGUF?
It depends on the quant: Q2_K is 4.3 GB, Q3_K_S is 5.0 GB, Q3_K_M is 5.5 GB, Q3_K_L is 5.9 GB, IQ4_XS is 6.1 GB, Q4_K_S is 6.4 GB and 5 more.
What context length does L3.0 Upscale 1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.5 GB at 8K and 6.2 GB at 32K.
Where can I download L3.0 Upscale 1 GGUF?
The files are on Hugging Face in the mradermacher/l3.0-upscale-1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.