PH

phi 2 code instruct

PhiGGUF by parsakUpdated 2024-01-18
Download on Hugging Face
Parameters2.78B
Context2K
Layers32
Architecturephi2
Smallest quant1.4 GB
Quick answer

phi 2 code instruct 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 7 quants, from 1.4 GB (Q3_K_M) to 5.6 GB (F16).

phi 2 code instruct is a 2.78B-parameter Phi model in GGUF format, quantized by parsak. Its trained context length is 2K tokens. The repository has 7 quant files, from 1.4 GB (Q3_K_M) to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.4 GB 2.6 GB
Fits Get file →
Q4_01.6 GB 2.8 GB
Fits Get file →
Q4_K_M1.7 GB 2.9 GB
Fits Get file →
Q5_K_M2.0 GB 3.2 GB
Fits Get file →
Q6_K2.3 GB 3.5 GB
Fits Get file →
Q8_03.0 GB 4.1 GB
Fits Get file →
F165.6 GB 6.7 GB
Fits Get file →

What GPU do you need for phi 2 code instruct?

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 Q6_K (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.7 GB in use).

Which phi 2 code instruct quant should you choose?

Q4_K_M is the usual starting point for phi 2 code instruct: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 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 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

Architecturephi2
Parameters2.78B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byparsak
FamilyPhi
Licenseapache-2.0
Downloads (HF)108
Last updated2024-01-18

Frequently asked questions about phi 2 code instruct

How much VRAM does phi 2 code instruct 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 code instruct on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 2 code instruct GGUF?

It depends on the quant: Q3_K_M is 1.4 GB, Q4_0 is 1.6 GB, Q4_K_M is 1.7 GB, Q5_K_M is 2.0 GB, Q6_K is 2.3 GB, Q8_0 is 3.0 GB and 1 more.

What context length does phi 2 code instruct 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 code instruct GGUF?

The files are on Hugging Face in the parsak/phi-2-code-instruct-gguf 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 2 code instruct 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.

Other GGUFs of phi-2-code-instruct

Similar models

Browse all →

More from parsak

All by parsak →

More Phi models

All Phi →

Other tiny models

All tiny models →