phi 2 needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.4 GB (Q3_K_M) to 1.7 GB (Q4_K_M).
phi 2 is a 2.78B-parameter Phi model in GGUF format, quantized by Soon16. Its trained context length is 2K tokens. The repository has 2 quant files, from 1.4 GB (Q3_K_M) to 1.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.4 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 2.9 GB | Fits | Get file → |
What GPU do you need for phi 2?
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 Q4_K_M (1.7 GB file, about 4.9 GB in use).
Which phi 2 quant should you choose?
Q4_K_M is the usual starting point for phi 2: it balances file size and quality well. Here it is a 1.7 GB file.
If memory is tight, the smallest file is Q3_K_M at 1.4 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
Frequently asked questions about phi 2
How much VRAM does phi 2 need?
About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 phi 2 on an 8 GB GPU?
Yes, with Q4_K_M: the 1.7 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi 2 GGUF?
It depends on the quant: Q3_K_M is 1.4 GB, Q4_K_M is 1.7 GB.
What context length does phi 2 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download phi 2 GGUF?
The files are on Hugging Face in the Soon16/phi-2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.