PE

Pearush phi moe 1e

PearushGGUF by RichardErkhovUpdated 2025-03-21
Download on Hugging Face
Parameters2.49B
Context128K
Layers32
Architecturephimoe
Smallest quant1.0 GB
Quick answer

Pearush phi moe 1e needs about 3.1 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.0 GB (Q2_K) to 2.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Pearush phi moe 1e is a 2.49B-parameter Pearush model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 22 quant files, from 1.0 GB (Q2_K) to 2.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 2.6 GB
Fits Get file →
IQ3_XS1.1 GB 2.7 GB
Fits Get file →
Q3_K_S1.2 GB 2.7 GB
Fits Get file →
IQ3_S1.2 GB 2.8 GB
Fits Get file →
IQ3_M1.3 GB 2.8 GB
Fits Get file →
Q3_K1.3 GB 2.9 GB
Fits Get file →
Q3_K_M1.3 GB 2.9 GB
Fits Get file →
Q3_K_L1.4 GB 3.0 GB
Fits Get file →
IQ4_XS1.4 GB 3.0 GB
Fits Get file →
Q4_01.4 GB 3.0 GB
Fits Get file →
IQ4_NL1.5 GB 3.0 GB
Fits Get file →
Q4_K_S1.5 GB 3.1 GB
Fits Get file →
Q4_K1.5 GB 3.1 GB
Fits Get file →
Q4_K_M1.5 GB 3.1 GB
Fits Get file →
Q4_11.6 GB 3.2 GB
Fits Get file →
Q5_01.7 GB 3.3 GB
Fits Get file →
Q5_K_S1.7 GB 3.3 GB
Fits Get file →
Q5_K1.8 GB 3.4 GB
Fits Get file →
Q5_K_M1.8 GB 3.4 GB
Fits Get file →
Q5_11.9 GB 3.5 GB
Fits Get file →
Q6_K2.1 GB 3.7 GB
Fits Get file →
Q8_02.6 GB 4.2 GB
Fits Get file →

What GPU do you need for Pearush phi moe 1e?

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: the best quant that fits is Q6_K (2.1 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.6 GB file, about 4.2 GB in use).

Which Pearush phi moe 1e quant should you choose?

Q4_K_M is the usual starting point for Pearush phi moe 1e: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.6 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 Q2_K at 1.0 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

Architecturephimoe
Parameters2.49B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyPearush
Downloads (HF)136
Last updated2025-03-21

Frequently asked questions about Pearush phi moe 1e

How much VRAM does Pearush phi moe 1e need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.5 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 Pearush phi moe 1e on an 8 GB GPU?

Yes, with Q8_0: the 2.6 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pearush phi moe 1e GGUF?

It depends on the quant: Q2_K is 1.0 GB, IQ3_XS is 1.1 GB, Q3_K_S is 1.2 GB, IQ3_S is 1.2 GB, IQ3_M is 1.3 GB, Q3_K is 1.3 GB and 16 more.

What context length does Pearush phi moe 1e support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Pearush phi moe 1e GGUF?

The files are on Hugging Face in the RichardErkhov/Pearush_-_phi_moe_1e-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Pearush models

All Pearush →

Other tiny models

All tiny models →