GO

GOAT Adapt MoE 4x7B

GoatGGUF by senseableUpdated 2024-01-10
Download on Hugging Face
Parameters19.7B
Context2K
Layers32
Architecturellama
Smallest quant13.6 GB
Quick answer

GOAT Adapt MoE 4x7B needs about 18.4 GB of memory at Q5_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 24 GB GPU.

GOAT Adapt MoE 4x7B is a 19.7B-parameter Goat model in GGUF format, quantized by senseable. Its trained context length is 2K tokens. The repository has 1 quant file, from 13.6 GB (Q5_K_M) to 13.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M13.6 GB 15.2 GB
Too big Get file →

What GPU do you need for GOAT Adapt MoE 4x7B?

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 Q5_K_M (13.6 GB file, about 18.4 GB in use).

Which GOAT Adapt MoE 4x7B quant should you choose?

Q5_K_M (13.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters19.7B (approximate, mixture of experts)
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bysenseable
FamilyGoat
Downloads (HF)22
Last updated2024-01-10

Frequently asked questions about GOAT Adapt MoE 4x7B

How much VRAM does GOAT Adapt MoE 4x7B need?

About 18.4 GB at Q5_K_M with an 8K context window. That is the 13.6 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 GOAT Adapt MoE 4x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GOAT Adapt MoE 4x7B GGUF?

It depends on the quant: Q5_K_M is 13.6 GB.

What context length does GOAT Adapt MoE 4x7B 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 GOAT Adapt MoE 4x7B GGUF?

The files are on Hugging Face in the senseable/GOAT-Adapt-MoE-4x7B-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 senseable

All by senseable →

More Goat models

All Goat →

Other medium models

All medium models →