PH

phi 4

PhiGGUF by microsoftUpdated 2025-11-24
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturephi3
Smallest quant3.6 GB
Quick answer

phi 4 needs about 10.6 GB of memory at Q4_0 (a 8.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 23 quants, from 3.6 GB (TQ1_0) to 29.3 GB (BF16).

Phi‑4: 15 B parameter coding‑focused LLM

Phi‑4 is a 15 billion‑parameter model built on the phi3 architecture. It is trained on a mix of public documents, synthetic textbook data, academic books, and chat‑style supervised data. The model supports a 16 384‑token context window and is released under the MIT license.

Good at

  • Coding tasks
  • Instruction following
  • General knowledge

Limits

  • Large VRAM requirement for higher quants
  • No vision or multimodal support
  • Limited language coverage

Best for

  • Developers needing code generation
  • Researchers testing language understanding
  • Educators creating educational content

Who it’s for. The model is suitable for developers and researchers who require a large, open‑source LLM focused on coding and instruction following. It is ideal for those who can allocate sufficient GPU memory and prefer a permissive MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_03.6 GB 5.8 GB
Fits Get file →
TQ2_04.2 GB 6.4 GB
Fits Get file →
Q2_K5.5 GB 7.7 GB
Tight Get file →
IQ3_XXS6.1 GB 8.3 GB
Too big Get file →
IQ3_XS6.2 GB 8.4 GB
Too big Get file →
IQ3_S6.5 GB 8.7 GB
Too big Get file →
Q3_K_S6.5 GB 8.7 GB
Too big Get file →
IQ3_M6.9 GB 9.1 GB
Too big Get file →
Q3_K7.4 GB 9.5 GB
Too big Get file →
Q3_K_L7.9 GB 10.1 GB
Too big Get file →
IQ4_XS8.0 GB 10.2 GB
Too big Get file →
Q4_08.4 GB 10.6 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
Q4_K_S8.4 GB 10.6 GB
Too big Get file →
Q4_K9.1 GB 11.2 GB
Too big Get file →
Q4_19.3 GB 11.4 GB
Too big Get file →
Q5_010.2 GB 12.3 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
Q5_K10.6 GB 12.8 GB
Too big Get file →
Q5_111.0 GB 13.2 GB
Too big Get file →
Q6_K12.0 GB 14.2 GB
Too big Get file →
Q8_015.6 GB 17.8 GB
Too big Get file →
BF1629.3 GB 31.5 GB
Too big Get file →

For 8 GB VRAM, use TQ1_0 (3.59 GB) or TQ2_0 (4.23 GB). With 12 GB VRAM, Q4_0 (8.38 GB) or Q4_K_S (8.44 GB) are suitable. For 16 GB VRAM, Q5_0 (10.15 GB) or Q5_K (10.6 GB) provide higher quality while staying within memory limits. Estimates are approximate.

What GPU do you need for phi 4?

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 TQ1_0 (3.6 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.5 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.3 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.3 GB file, about 31.5 GB in use).

Which phi 4 quant should you choose?

Q4_0 (8.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is TQ1_0 at 3.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymicrosoft
FamilyPhi
Licensemit
Downloads (HF)11,504
Last updated2025-11-24

Frequently asked questions about phi 4

How much VRAM does phi 4 need?

About 10.6 GB at Q4_0 with an 8K context window. That is the 8.4 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 4 on an 8 GB GPU?

Yes, with Q2_K: the 5.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 4 GGUF?

It depends on the quant: TQ1_0 is 3.6 GB, TQ2_0 is 4.2 GB, Q2_K is 5.5 GB, IQ3_XXS is 6.1 GB, IQ3_XS is 6.2 GB, IQ3_S is 6.5 GB and 17 more.

What context length does phi 4 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download phi 4 GGUF?

The files are on Hugging Face in the microsoft/phi-4-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 4 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.

Can I run Phi‑4 on 8 GB VRAM?

Yes, using the TQ1_0 or TQ2_0 quantizations which fit within 8 GB of VRAM with an estimated 5.8–6.4 GB usage at 8K context.

Does Phi‑4 support image inputs?

No, Phi‑4 is a text‑only model with no vision or multimodal capabilities.

Similar models

Browse all →

More from microsoft

All by microsoft →

More Phi models

All Phi →

Other medium models

All medium models →