PH

phi 4

PhiGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturephi3
Smallest quant3.3 GB
Quick answer

phi 4 needs about 11.2 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 34 quants, from 3.3 GB (IQ1_S) to 29.3 GB (BF16).

Phi 4 – 14.7B parameter Phi3 architecture

Phi 4 is a 14.7B parameter Phi3 model trained on 16384 context tokens. It is released under the MIT license and focuses on coding tasks. The model is available in multiple quantized GGUF formats.

Good at

  • Coding tasks
  • Text generation
  • Prompt completion

Limits

  • No vision support
  • Large memory requirement for high‑precision quants
  • No mixture of experts

Best for

  • Local code generation
  • Educational coding assistants
  • Rapid prototyping of coding tools

Who it’s for. Developers and researchers who need a compact Phi3 model for coding applications. The model is suitable for local deployment on GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.3 GB 5.5 GB
Fits Get file →
TQ1_03.6 GB 5.8 GB
Fits Get file →
IQ1_M3.6 GB 5.8 GB
Fits Get file →
IQ2_XXS4.1 GB 6.3 GB
Fits Get file →
TQ2_04.2 GB 6.4 GB
Fits Get file →
IQ2_XS4.5 GB 6.7 GB
Fits Get file →
IQ2_S4.7 GB 6.9 GB
Fits Get file →
IQ2_M5.1 GB 7.3 GB
Tight Get file →
Q2_K_S5.2 GB 7.4 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 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_K_M7.4 GB 9.5 GB
Too big Get file →
IQ4_XS7.9 GB 10.1 GB
Too big Get file →
Q4_08.3 GB 10.4 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_K_M9.1 GB 11.2 GB
Too big Get file →
Q4_19.2 GB 11.3 GB
Too big Get file →
Q5_010.1 GB 12.3 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
BF1610.4 GB 12.6 GB
Too big Get file →
F1610.4 GB 12.6 GB
Too big Get file →
Q5_K_M10.6 GB 12.8 GB
Too big Get file →
Q5_111.0 GB 13.2 GB
Too big Get file →
Q6_K_M12.0 GB 14.2 GB
Too big Get file →
BF1613.2 GB 15.4 GB
Too big Get file →
F1613.2 GB 15.4 GB
Too big Get file →
Q8_015.6 GB 17.8 GB
Too big Get file →
BF1616.5 GB 18.7 GB
Too big Get file →
F1616.5 GB 18.7 GB
Too big Get file →
BF1629.3 GB 31.5 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (3.32 GB, 5.5 GB memory at 8k context) or TQ1_0 (3.59 GB, 5.8 GB). For 12 GB VRAM use Q4_K_M (9.05 GB, 11.2 GB). For 16 GB VRAM use Q8_0 (15.58 GB, 17.8 GB). 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 IQ1_M (3.6 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.2 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (13.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.5 GB file, about 18.7 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_K_M is the usual starting point for phi 4: it balances file size and quality well. Here it is a 9.1 GB file.

The Q8_0 file is 15.6 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 IQ1_S at 3.3 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
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized byMungert
FamilyPhi
Licensemit
Downloads (HF)623
Last updated2025-09-24

Frequently asked questions about phi 4

How much VRAM does phi 4 need?

About 11.2 GB at Q4_K_M with an 8K context window. That is the 9.1 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 phi 4 on an 8 GB GPU?

Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 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: IQ1_S is 3.3 GB, TQ1_0 is 3.6 GB, IQ1_M is 3.6 GB, IQ2_XXS is 4.1 GB, TQ2_0 is 4.2 GB, IQ2_XS is 4.5 GB and 28 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 Mungert/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 IQ1_S or TQ1_0 quantizations, which require about 5.5–5.8 GB memory at 8k context.

Does Phi 4 support vision tasks?

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

Similar models

Browse all →

More from Mungert

All by Mungert →

More Phi models

All Phi →

Other medium models

All medium models →