PH

PhoGPT-7B5-Instruct

PhogptGGUF by nguyenvietUpdated 2024-01-20
Download on Hugging Face
Parameters8.5B
Context2K
Layers32
Architecturempt
Smallest quant3.8 GB
Quick answer

PhoGPT-7B5-Instruct needs about 10.3 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.8 GB (Q2_K) to 17.0 GB (F16).

PhoGPT-7B5-Instruct is a 8.5B-parameter Phogpt model in GGUF format, quantized by nguyenviet. Its trained context length is 2K tokens. The repository has 15 quant files, from 3.8 GB (Q2_K) to 17.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 5.4 GB
Fits Get file →
Q3_K_S4.1 GB 5.6 GB
Fits Get file →
Q3_K_M4.7 GB 6.2 GB
Fits Get file →
Q3_K_L5.0 GB 6.6 GB
Fits Get file →
Q4_05.1 GB 6.6 GB
Fits Get file →
Q4_K_S5.1 GB 6.7 GB
Fits Get file →
Q4_15.5 GB 7.1 GB
Fits Get file →
Q4_K_M5.5 GB 7.1 GB
Fits Get file →
Q5_06.0 GB 7.6 GB
Tight Get file →
Q5_K_S6.0 GB 7.6 GB
Tight Get file →
Q5_K_M6.4 GB 7.9 GB
Tight Get file →
Q5_16.5 GB 8.0 GB
Too big Get file →
Q6_K7.0 GB 8.6 GB
Too big Get file →
Q8_09.0 GB 10.6 GB
Too big Get file →
F1617.0 GB 18.6 GB
Too big Get file →

What GPU do you need for PhoGPT-7B5-Instruct?

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 Q6_K (7.0 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 13.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.0 GB file, about 21.8 GB in use).

Which PhoGPT-7B5-Instruct quant should you choose?

Q4_K_M is the usual starting point for PhoGPT-7B5-Instruct: it balances file size and quality well. Here it is a 5.5 GB file.

The Q8_0 file is 9.0 GB, about 1.6 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 3.8 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

Architecturempt
Parameters8.5B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bynguyenviet
FamilyPhogpt
Licenseother
Downloads (HF)244
Last updated2024-01-20

Frequently asked questions about PhoGPT-7B5-Instruct

How much VRAM does PhoGPT-7B5-Instruct need?

About 10.3 GB at Q4_K_M with an 8K context window. That is the 5.5 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 PhoGPT-7B5-Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PhoGPT-7B5-Instruct GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.1 GB, Q3_K_M is 4.7 GB, Q3_K_L is 5.0 GB, Q4_0 is 5.1 GB, Q4_K_S is 5.1 GB and 9 more.

What context length does PhoGPT-7B5-Instruct support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download PhoGPT-7B5-Instruct GGUF?

The files are on Hugging Face in the nguyenviet/PhoGPT-7B5-Instruct-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 PhoGPT-7B5-Instruct use?

Hugging Face lists the license as other. 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 nguyenviet

All by nguyenviet →

More Phogpt models

All Phogpt →

Other small models

All small models →