PH

phi 4 abliterated Orion 18B Q8 0

PhiGGUF by OtakadelicUpdated 2025-05-01
Download on Hugging Face
Parameters18.1B
Context16K
Layers50
Architecturephi3
Smallest quant19.2 GB
Quick answer

phi 4 abliterated Orion 18B Q8 0 needs about 21.8 GB of memory at Q8_0 (a 19.2 GB file) with an 8K context window, so it fits on a 24 GB GPU.

phi 4 abliterated Orion 18B Q8 0 is a 18.1B-parameter Phi model in GGUF format, quantized by Otakadelic. Its trained context length is 16K tokens. The repository has 1 quant file, from 19.2 GB (Q8_0) to 19.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_019.2 GB 21.8 GB
Too big Get file →

What GPU do you need for phi 4 abliterated Orion 18B Q8 0?

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: the best quant that fits is Q8_0 (19.2 GB file, about 21.8 GB in use).

Which phi 4 abliterated Orion 18B Q8 0 quant should you choose?

Q8_0 (19.2 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
Parameters18.1B
Layers50
Trained context16,384 tokens
KV cache (fp16)250 KB per token

Source

Quantized byOtakadelic
FamilyPhi
Licensegpl-3.0
Downloads (HF)18
Last updated2025-05-01

Frequently asked questions about phi 4 abliterated Orion 18B Q8 0

How much VRAM does phi 4 abliterated Orion 18B Q8 0 need?

About 21.8 GB at Q8_0 with an 8K context window. That is the 19.2 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 4 abliterated Orion 18B Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi 4 abliterated Orion 18B Q8 0 GGUF?

It depends on the quant: Q8_0 is 19.2 GB.

What context length does phi 4 abliterated Orion 18B Q8 0 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.

Where can I download phi 4 abliterated Orion 18B Q8 0 GGUF?

The files are on Hugging Face in the Otakadelic/phi-4-abliterated-Orion-18B-Q8_0-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 4 abliterated Orion 18B Q8 0 use?

Hugging Face lists the license as gpl-3.0. 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-4-abliterated-Orion-18B

Similar models

Browse all →

More from Otakadelic

All by Otakadelic →

More Phi models

All Phi →

Other medium models

All medium models →