PH

WAIDWML Phi4 8x14B Bf16

PhiGGUF by mradermacherUpdated 2025-02-22
Download on Hugging Face
Parameters91.7B
Context16K
Layers40
Architecturellama
Smallest quant34.1 GB
Quick answer

WAIDWML Phi4 8x14B Bf16 needs about 46.5 GB of memory at BF16 (a 44.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 34.1 GB (BF16) to 49.9 GB (BF16).

WAIDWML Phi4 8x14B Bf16 is a 91.7B-parameter Phi model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 5 quant files, from 34.1 GB (BF16) to 49.9 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1634.1 GB 36.3 GB
Too big Get file →
BF1640.2 GB 42.4 GB
Too big Get file →
BF1644.3 GB 46.5 GB
Too big Get file →
BF1647.5 GB 49.7 GB
Too big Get file →
BF1649.9 GB 52.1 GB
Too big Get file →

What GPU do you need for WAIDWML Phi4 8x14B Bf16?

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: the best quant that fits is BF16 (44.3 GB file, about 46.5 GB in use).

Which WAIDWML Phi4 8x14B Bf16 quant should you choose?

BF16 (44.3 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.

If memory is tight, the smallest file is BF16 at 34.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters91.7B (approximate, mixture of experts)
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)29
Last updated2025-02-22

Frequently asked questions about WAIDWML Phi4 8x14B Bf16

How much VRAM does WAIDWML Phi4 8x14B Bf16 need?

About 46.5 GB at BF16 with an 8K context window. That is the 44.3 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 WAIDWML Phi4 8x14B Bf16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 36.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WAIDWML Phi4 8x14B Bf16 GGUF?

It depends on the quant: BF16 is 34.1 GB, BF16 is 40.2 GB, BF16 is 44.3 GB, BF16 is 47.5 GB, BF16 is 49.9 GB.

What context length does WAIDWML Phi4 8x14B Bf16 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download WAIDWML Phi4 8x14B Bf16 GGUF?

The files are on Hugging Face in the mradermacher/WAIDWML-Phi4-8x14B-bf16-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 WAIDWML Phi4 8x14B Bf16 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other large models

All large models →