PH

Phi 3.5 Sakura Yuzu v1.5

PhiGGUF by win10Updated 2024-10-16
Download on Hugging Face
Parameters7.22B
Context4K
Layers62
Architecturephi3
Smallest quant7.7 GB
Quick answer

Phi 3.5 Sakura Yuzu v1.5 needs about 14.4 GB of memory at Q8_0 (a 7.7 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Phi 3.5 Sakura Yuzu v1.5 is a 7.22B-parameter Phi model in GGUF format, quantized by win10. Its trained context length is 4K tokens. The repository has 1 quant file, from 7.7 GB (Q8_0) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.7 GB 11.3 GB
Too big Get file →

What GPU do you need for Phi 3.5 Sakura Yuzu v1.5?

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 Q8_0 (7.7 GB file, about 14.4 GB in use).

Which Phi 3.5 Sakura Yuzu v1.5 quant should you choose?

Q8_0 (7.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters7.22B
Layers62
Trained context4,096 tokens
KV cache (fp16)744 KB per token

Source

Quantized bywin10
FamilyPhi
Downloads (HF)18
Last updated2024-10-16

Frequently asked questions about Phi 3.5 Sakura Yuzu v1.5

How much VRAM does Phi 3.5 Sakura Yuzu v1.5 need?

About 14.4 GB at Q8_0 with an 8K context window. That is the 7.7 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 Sakura Yuzu v1.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi 3.5 Sakura Yuzu v1.5 GGUF?

It depends on the quant: Q8_0 is 7.7 GB.

What context length does Phi 3.5 Sakura Yuzu v1.5 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.2 GB at 8K and 3.1 GB at 4K.

Where can I download Phi 3.5 Sakura Yuzu v1.5 GGUF?

The files are on Hugging Face in the win10/phi-3.5-Sakura-Yuzu-v1.5-7.64b-Q8_0-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-3.5-Sakura-Yuzu-v1.5-7.64b

Similar models

Browse all →

More from win10

All by win10 →

More Phi models

All Phi →

Other small models

All small models →