FU

functionary medium v3.1

FunctionaryGGUF by meetkaiUpdated 2024-08-14
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant40.0 GB
Quick answer

functionary medium v3.1 needs about 43.2 GB of memory at Q4_0 (a 40.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

functionary medium v3.1 is a 70.6B-parameter Functionary model in GGUF format, quantized by meetkai. Its trained context length is 128K tokens. The repository has 1 quant file, from 40.0 GB (Q4_0) to 40.0 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_040.0 GB 43.2 GB
Too big Get file →

What GPU do you need for functionary medium v3.1?

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 Q4_0 (40.0 GB file, about 43.2 GB in use).

Which functionary medium v3.1 quant should you choose?

Q4_0 (40.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymeetkai
Downloads (HF)22
Last updated2024-08-14

Frequently asked questions about functionary medium v3.1

How much VRAM does functionary medium v3.1 need?

About 43.2 GB at Q4_0 with an 8K context window. That is the 40.0 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 functionary medium v3.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 43.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of functionary medium v3.1 GGUF?

It depends on the quant: Q4_0 is 40.0 GB.

What context length does functionary medium v3.1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download functionary medium v3.1 GGUF?

The files are on Hugging Face in the meetkai/functionary-medium-v3.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from meetkai

All by meetkai →

More Functionary models

All Functionary →

Other large models

All large models →