PH

Phi Stoma

PhiGGUF by mradermacherUpdated 2024-12-23
Download on Hugging Face
Parameters7.81B
Context2K
Layers96
Architecturephi2
Smallest quant3.0 GB
Quick answer

Phi Stoma needs about 13.4 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 3.0 GB (Q2_K) to 15.6 GB (F16).

Phi Stoma is a 7.81B-parameter Phi model in GGUF format, quantized by mradermacher. Its trained context length is 2K tokens. The repository has 12 quant files, from 3.0 GB (Q2_K) to 15.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 5.5 GB
Fits Get file →
Q3_K_S3.4 GB 5.9 GB
Fits Get file →
Q3_K_M3.9 GB 6.5 GB
Fits Get file →
IQ4_XS4.3 GB 6.8 GB
Fits Get file →
Q3_K_L4.4 GB 6.9 GB
Fits Get file →
Q4_K_S4.5 GB 7.0 GB
Fits Get file →
Q4_K_M4.8 GB 7.4 GB
Tight Get file →
Q5_K_S5.4 GB 7.9 GB
Tight Get file →
Q5_K_M5.6 GB 8.1 GB
Too big Get file →
Q6_K6.4 GB 8.9 GB
Too big Get file →
Q8_08.3 GB 10.8 GB
Too big Get file →
F1615.6 GB 18.1 GB
Too big Get file →

What GPU do you need for Phi Stoma?

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: the best quant that fits is Q3_K_S (3.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 16.9 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (15.6 GB file, about 24.2 GB in use).

Which Phi Stoma quant should you choose?

Q4_K_M is the usual starting point for Phi Stoma: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters7.81B
Layers96
Trained context2,048 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)190
Last updated2024-12-23

Frequently asked questions about Phi Stoma

How much VRAM does Phi Stoma need?

About 13.4 GB at Q4_K_M with an 8K context window. That is the 4.8 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 Stoma on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi Stoma GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.4 GB, Q3_K_M is 3.9 GB, IQ4_XS is 4.3 GB, Q3_K_L is 4.4 GB, Q4_K_S is 4.5 GB and 6 more.

What context length does Phi Stoma support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 8.1 GB at 8K and 2.0 GB at 2K.

Where can I download Phi Stoma GGUF?

The files are on Hugging Face in the mradermacher/Phi-Stoma-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 Stoma 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 small models

All small models →