PH

PHI4 SFT DE THINKING EXP Q8 0

PhiGGUF by avemio-digitalUpdated 2025-02-07
Download on Hugging Face
Parameters14.7B
Context34K
Layers40
Architecturellama
Smallest quant15.6 GB
Quick answer

PHI4 SFT DE THINKING EXP Q8 0 needs about 17.8 GB of memory at Q8_0 (a 15.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

PHI4 SFT DE THINKING EXP Q8 0 is a 14.7B-parameter Phi model in GGUF format, quantized by avemio-digital. Its trained context length is 34K tokens. The repository has 1 quant file, from 15.6 GB (Q8_0) to 15.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_015.6 GB 17.8 GB
Too big Get file →

What GPU do you need for PHI4 SFT DE THINKING EXP 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 (15.6 GB file, about 17.8 GB in use).

Which PHI4 SFT DE THINKING EXP Q8 0 quant should you choose?

Q8_0 (15.6 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

Architecturellama
Parameters14.7B
Layers40
Trained context35,000 tokens
KV cache (fp16)200 KB per token

Source

Quantized byavemio-digital
FamilyPhi
Downloads (HF)7
Last updated2025-02-07

Frequently asked questions about PHI4 SFT DE THINKING EXP Q8 0

How much VRAM does PHI4 SFT DE THINKING EXP Q8 0 need?

About 17.8 GB at Q8_0 with an 8K context window. That is the 15.6 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 PHI4 SFT DE THINKING EXP Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PHI4 SFT DE THINKING EXP Q8 0 GGUF?

It depends on the quant: Q8_0 is 15.6 GB.

What context length does PHI4 SFT DE THINKING EXP Q8 0 support?

The GGUF header lists a trained context length of 35,000 tokens (34K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download PHI4 SFT DE THINKING EXP Q8 0 GGUF?

The files are on Hugging Face in the avemio-digital/PHI4-SFT-DE-THINKING-EXP-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 PHI4-SFT-DE-THINKING-EXP

Similar models

Browse all →

More from avemio-digital

All by avemio-digital →

More Phi models

All Phi →

Other medium models

All medium models →