PH

Microsoft Phi3 14B Instruct128K

PhiGGUF by CHE-72-ZLabUpdated 2024-06-23
Download on Hugging Face
Parameters14B
Context128K
Layers40
Architecturephi3
Smallest quant5.1 GB
Quick answer

Microsoft Phi3 14B Instruct128K needs about 8.2 GB of memory at Q3_K_S (a 6.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.1 GB (Q2_K) to 6.9 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

Microsoft Phi3 14B Instruct128K is a 14B-parameter Phi model in GGUF format, quantized by CHE-72-ZLab. Its trained context length is 128K tokens. The repository has 3 quant files, from 5.1 GB (Q2_K) to 6.9 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.1 GB 7.3 GB
Tight Get file →
Q3_K_S6.1 GB 8.2 GB
Too big Get file →
Q3_K_M6.9 GB 9.1 GB
Too big Get file →

What GPU do you need for Microsoft Phi3 14B Instruct128K?

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 Q2_K (5.1 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (6.9 GB file, about 9.1 GB in use).

Which Microsoft Phi3 14B Instruct128K quant should you choose?

Q3_K_S (6.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K at 5.1 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

Architecturephi3
Parameters14B
Layers40
Trained context131,072 tokens
KV cache (fp16)200 KB per token

Source

Quantized byCHE-72-ZLab
FamilyPhi
Licensemit
Downloads (HF)140
Last updated2024-06-23

Frequently asked questions about Microsoft Phi3 14B Instruct128K

How much VRAM does Microsoft Phi3 14B Instruct128K need?

About 8.2 GB at Q3_K_S with an 8K context window. That is the 6.1 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 Microsoft Phi3 14B Instruct128K on an 8 GB GPU?

Yes, with Q2_K: the 5.1 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Microsoft Phi3 14B Instruct128K GGUF?

It depends on the quant: Q2_K is 5.1 GB, Q3_K_S is 6.1 GB, Q3_K_M is 6.9 GB.

What context length does Microsoft Phi3 14B Instruct128K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download Microsoft Phi3 14B Instruct128K GGUF?

The files are on Hugging Face in the CHE-72-ZLab/Microsoft-Phi3-14B-Instruct128K-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 Microsoft Phi3 14B Instruct128K use?

Hugging Face lists the license as mit. 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-3-mini-128k-instruct

Similar models

Browse all →

More from CHE-72-ZLab

All by CHE-72-ZLab →

More Phi models

All Phi →

Other medium models

All medium models →