Phi Lthy4 needs about 5.8 GB of memory at IQ2_S (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.8 GB (IQ1_S) to 6.9 GB (IQ4_NL).
Phi Lthy4 is a 11.9B-parameter Phi model in GGUF format, quantized by SicariusSicariiStuff. Its trained context length is 16K tokens. The repository has 10 quant files, from 2.8 GB (IQ1_S) to 6.9 GB (IQ4_NL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.8 GB | 4.7 GB | Fits | Get file → | |
| IQ1_M | 3.1 GB | 4.9 GB | Fits | Get file → | |
| IQ2_XXS | 3.4 GB | 5.3 GB | Fits | Get file → | |
| IQ2_XS | 3.8 GB | 5.6 GB | Fits | Get file → | |
| IQ2_S | 4.0 GB | 5.8 GB | Fits | Get file → | |
| IQ2_M | 4.3 GB | 6.1 GB | Fits | Get file → | |
| IQ3_XXS | 4.8 GB | 6.6 GB | Fits | Get file → | |
| IQ3_XS | 5.1 GB | 6.9 GB | Fits | Get file → | |
| IQ4_XS | 6.5 GB | 8.4 GB | Too big | Get file → | |
| IQ4_NL | 6.9 GB | 8.7 GB | Too big | Get file → |
What GPU do you need for Phi Lthy4?
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: the best quant that fits is IQ2_S (4.0 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (5.1 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_NL (6.9 GB file, about 8.7 GB in use).
Which Phi Lthy4 quant should you choose?
IQ2_S (4.0 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 2.8 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 Phi Lthy4
How much VRAM does Phi Lthy4 need?
About 5.8 GB at IQ2_S with an 8K context window. That is the 4.0 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 Phi Lthy4 on an 8 GB GPU?
Yes, with IQ3_XS: the 5.1 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Phi Lthy4 GGUF?
It depends on the quant: IQ1_S is 2.8 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 4 more.
What context length does Phi Lthy4 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.3 GB at 8K and 2.7 GB at 16K.
Where can I download Phi Lthy4 GGUF?
The files are on Hugging Face in the SicariusSicariiStuff/Phi-lthy4_iMatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Phi Lthy4 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.