PH

phi 3.5 moe cpu offload

PhiGGUF by MikeKuykendallUpdated 2025-10-08
Download on Hugging Face
Parameters41.9B
Context128K
Layers32
Architecturephimoe
Smallest quant83.8 GB
Quick answer

phi 3.5 moe cpu offload needs about 85.3 GB of memory at F16 (a 83.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

phi 3.5 moe cpu offload is a 41.9B-parameter Phi model in GGUF format, quantized by MikeKuykendall. Its trained context length is 128K tokens. The repository has 1 quant file, from 83.8 GB (F16) to 83.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1683.8 GB 85.3 GB
Too big Get file →

What GPU do you need for phi 3.5 moe cpu offload?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which phi 3.5 moe cpu offload quant should you choose?

F16 (83.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephimoe
Parameters41.9B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMikeKuykendall
FamilyPhi
Licensemit
Downloads (HF)17
Last updated2025-10-08

Frequently asked questions about phi 3.5 moe cpu offload

How much VRAM does phi 3.5 moe cpu offload need?

About 85.3 GB at F16 with an 8K context window. That is the 83.8 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 3.5 moe cpu offload on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 85.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi 3.5 moe cpu offload GGUF?

It depends on the quant: F16 is 83.8 GB.

What context length does phi 3.5 moe cpu offload 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 phi 3.5 moe cpu offload GGUF?

The files are on Hugging Face in the MikeKuykendall/phi-3.5-moe-cpu-offload-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 3.5 moe cpu offload 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.

Other GGUFs of Phi-3.5-MoE-instruct

Similar models

Browse all →

More from MikeKuykendall

All by MikeKuykendall →

More Phi models

All Phi →

Other large models

All large models →