PH

phi 4

PhiGGUF by unslothUpdated 2025-01-13
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant5.6 GB
Quick answer

phi 4 needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 5.6 GB (Q2_K) to 29.3 GB (F16).

Phi‑4: 15‑billion‑parameter Llama‑style model focused on coding and reasoning

Phi‑4 is a 15‑billion‑parameter Llama‑based model released under the MIT license. It supports a 16,384‑token context window and is optimized for code generation and general reasoning tasks. The model is available in multiple GGUF quantizations for efficient deployment.

Good at

  • Code generation
  • Reasoning tasks
  • Large context handling

Limits

  • No vision support
  • Requires at least 8‑k context for memory estimates
  • MIT license limits commercial use without attribution

Best for

  • Fine‑tuning on coding datasets
  • Chatbot development with long context
  • Educational tutoring in math and programming

Who it’s for. Developers and researchers needing a versatile, open‑source LLM for code and reasoning. The model is suitable for those who can fine‑tune or run it in llama.cpp environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.6 GB 7.8 GB
Tight Get file →
Q2_K_L5.7 GB 7.9 GB
Tight Get file →
Q3_K_M7.2 GB 9.4 GB
Too big Get file →
Q4_K_M8.9 GB 11.1 GB
Too big Get file →
Q5_K_M10.4 GB 12.6 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 →
F1629.3 GB 31.5 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (8.89 GB file, ~11.1 GB RAM). For 12‑GB VRAM, Q5_K_M (10.41 GB file, ~12.6 GB RAM). For 16‑GB VRAM, Q6_K (12.03 GB file, ~14.2 GB RAM). Higher‑precision quants increase accuracy but require more memory.

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K_L (5.7 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 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 F16 (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 8.9 GB file.

The Q8_0 file is 15.6 GB, about 1.8 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 Q2_K at 5.6 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

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

Source

Quantized byunsloth
FamilyPhi
Base modelmicrosoft/phi-4
Licensemit
Downloads (HF)7,957
Last updated2025-01-13

Frequently asked questions about phi 4

How much VRAM does phi 4 need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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_L: the 5.7 GB file needs about 7.9 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: Q2_K is 5.6 GB, Q2_K_L is 5.7 GB, Q3_K_M is 7.2 GB, Q4_K_M is 8.9 GB, Q5_K_M is 10.4 GB, Q6_K is 12.0 GB and 2 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 unsloth/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, with the Q4_K_M quantization which requires about 11.1 GB of RAM at 8‑k context.

Does Phi‑4 support image inputs?

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

Other GGUFs of phi-4

Similar models

Browse all →

More from unsloth

All by unsloth →

More Phi models

All Phi →

Other medium models

All medium models →