PH

phi 4 45b i1

PhiGGUF by mradermacherUpdated 2025-01-17
Download on Hugging Face
Parameters45.3B
Context16K
Layers130
Architecturephi3
Smallest quant9.6 GB
Quick answer

phi 4 45b i1 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 23 quants, from 9.6 GB (IQ1_S) to 37.2 GB (Q6_K).

phi 4 45b i1 is a 45.3B-parameter Phi model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 23 quant files, from 9.6 GB (IQ1_S) to 37.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S9.6 GB 15.5 GB
Too big Get file →
IQ1_M10.5 GB 16.5 GB
Too big Get file →
IQ2_XXS12.1 GB 18.0 GB
Too big Get file →
IQ2_XS13.4 GB 19.3 GB
Too big Get file →
IQ2_S14.1 GB 20.0 GB
Too big Get file →
IQ2_M15.3 GB 21.3 GB
Too big Get file →
Q2_K_S15.5 GB 21.4 GB
Too big Get file →
Q2_K16.7 GB 22.6 GB
Too big Get file →
IQ3_XXS17.7 GB 23.7 GB
Too big Get file →
IQ3_XS18.9 GB 24.8 GB
Too big Get file →
IQ3_S19.7 GB 25.6 GB
Too big Get file →
Q3_K_S19.7 GB 25.6 GB
Too big Get file →
IQ3_M21.0 GB 27.0 GB
Too big Get file →
Q3_K_M22.5 GB 28.4 GB
Too big Get file →
IQ4_XS24.2 GB 30.2 GB
Too big Get file →
Q3_K_L24.3 GB 30.3 GB
Too big Get file →
Q4_025.7 GB 31.7 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 →
Q4_128.4 GB 34.4 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 →

What GPU do you need for phi 4 45b i1?

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: the best quant that fits is IQ1_S (9.6 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XXS (17.7 GB file, about 23.7 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 i1 quant should you choose?

Q4_K_M is the usual starting point for phi 4 45b i1: it balances file size and quality well. Here it is a 27.8 GB file.

If memory is tight, the smallest file is IQ1_S at 9.6 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

Architecturephi3
Parameters45.3B
Layers130
Trained context16,384 tokens
KV cache (fp16)650 KB per token

Source

Quantized bymradermacher
FamilyPhi
Downloads (HF)187
Last updated2025-01-17

Frequently asked questions about phi 4 45b i1

How much VRAM does phi 4 45b i1 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 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi 4 45b i1 GGUF?

It depends on the quant: IQ1_S is 9.6 GB, IQ1_M is 10.5 GB, IQ2_XXS is 12.1 GB, IQ2_XS is 13.4 GB, IQ2_S is 14.1 GB, IQ2_M is 15.3 GB and 17 more.

What context length does phi 4 45b i1 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 i1 GGUF?

The files are on Hugging Face in the mradermacher/phi-4-45b-i1-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 →