PH

Phi 3.5 Mini Hyper Q4 K M

PhiGGUF by bunnycoreUpdated 2024-09-11
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant2.4 GB
Quick answer

Phi 3.5 Mini Hyper Q4 K M needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3.5 Mini Hyper Q4 K M is a 3.82B-parameter Phi model in GGUF format, quantized by bunnycore. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.4 GB (Q4_K_M) to 2.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.4 GB 6.1 GB
Fits Get file →

What GPU do you need for Phi 3.5 Mini Hyper Q4 K M?

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: the best quant that fits is Q4_K_M (2.4 GB file, about 6.1 GB in use).

Which Phi 3.5 Mini Hyper Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Phi 3.5 Mini Hyper Q4 K M: it balances file size and quality well. Here it is a 2.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bybunnycore
FamilyPhi
Downloads (HF)24
Last updated2024-09-11

Frequently asked questions about Phi 3.5 Mini Hyper Q4 K M

How much VRAM does Phi 3.5 Mini Hyper Q4 K M need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Mini Hyper Q4 K M on an 8 GB GPU?

Yes, with Q4_K_M: the 2.4 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3.5 Mini Hyper Q4 K M GGUF?

It depends on the quant: Q4_K_M is 2.4 GB.

What context length does Phi 3.5 Mini Hyper Q4 K M support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Phi 3.5 Mini Hyper Q4 K M GGUF?

The files are on Hugging Face in the bunnycore/Phi-3.5-Mini-Hyper-Q4_K_M-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-Mini-Hyper

Similar models

Browse all →

More from bunnycore

All by bunnycore →

More Phi models

All Phi →

Other small models

All small models →