PH

phi 4 45b

PhiGGUF by mradermacherUpdated 2025-01-17
Download on Hugging Face
Parameters45.3B
Context16K
Layers130
Architecturephi3
Smallest quant16.7 GB
Quick answer

phi 4 45b needs about 33.8 GB of memory at Q4_K_M (a 27.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 16.7 GB (Q2_K) to 48.2 GB (Q8_0).

phi 4 45b is a 45.3B-parameter Phi model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 11 quant files, from 16.7 GB (Q2_K) to 48.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K16.7 GB 22.6 GB
Too big Get file →
Q3_K_S19.7 GB 25.6 GB
Too big Get file →
Q3_K_M22.5 GB 28.4 GB
Too big Get file →
Q3_K_L24.3 GB 30.3 GB
Too big Get file →
IQ4_XS24.5 GB 30.4 GB
Too big Get file →
Q4_K_S25.8 GB 31.8 GB
Too big Get file →
Q4_K_M27.8 GB 33.8 GB
Too big Get file →
Q5_K_S31.2 GB 37.2 GB
Too big Get file →
Q5_K_M32.7 GB 38.7 GB
Too big Get file →
Q6_K37.2 GB 43.1 GB
Too big Get file →
Q8_048.2 GB 54.1 GB
Too big Get file →

What GPU do you need for phi 4 45b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q2_K (16.7 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_S (25.8 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (37.2 GB file, about 43.1 GB in use).

Which phi 4 45b quant should you choose?

Q4_K_M is the usual starting point for phi 4 45b: it balances file size and quality well. Here it is a 27.8 GB file.

The Q8_0 file is 48.2 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 Q2_K at 16.7 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
Parameters45.3B
Layers130
Trained context16,384 tokens
KV cache (fp16)650 KB per token

Source

Quantized bymradermacher
FamilyPhi
Downloads (HF)35
Last updated2025-01-17

Frequently asked questions about phi 4 45b

How much VRAM does phi 4 45b need?

About 33.8 GB at Q4_K_M with an 8K context window. That is the 27.8 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 45b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi 4 45b GGUF?

It depends on the quant: Q2_K is 16.7 GB, Q3_K_S is 19.7 GB, Q3_K_M is 22.5 GB, Q3_K_L is 24.3 GB, IQ4_XS is 24.5 GB, Q4_K_S is 25.8 GB and 5 more.

What context length does phi 4 45b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 5.5 GB at 8K and 10.9 GB at 16K.

Where can I download phi 4 45b GGUF?

The files are on Hugging Face in the mradermacher/phi-4-45b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of phi-4-45b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other large models

All large models →