FU

functionary medium v2.2 q6 K

FunctionaryGGUF by casualjimUpdated 2024-02-11
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant38.4 GB
Quick answer

functionary medium v2.2 q6 K needs about 40.0 GB of memory at Q6_K (a 38.4 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 4.3 GB.

functionary medium v2.2 q6 K is a 46.7B-parameter Functionary model in GGUF format, quantized by casualjim. Its trained context length is 32K tokens. The repository has 1 quant file, from 38.4 GB (Q6_K) to 38.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K38.4 GB 40.0 GB
Too big Get file →

What GPU do you need for functionary medium v2.2 q6 K?

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 Q6_K (38.4 GB file, about 40.0 GB in use).

Which functionary medium v2.2 q6 K quant should you choose?

Q6_K (38.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bycasualjim
Downloads (HF)8
Last updated2024-02-11

Frequently asked questions about functionary medium v2.2 q6 K

How much VRAM does functionary medium v2.2 q6 K need?

About 40.0 GB at Q6_K with an 8K context window. That is the 38.4 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 v2.2 q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 40.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of functionary medium v2.2 q6 K GGUF?

It depends on the quant: Q6_K is 38.4 GB.

What context length does functionary medium v2.2 q6 K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download functionary medium v2.2 q6 K GGUF?

The files are on Hugging Face in the casualjim/functionary-medium-v2.2-q6_K-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 casualjim

All by casualjim →

More Functionary models

All Functionary →

Other large models

All large models →