MP

mpt 30b chat q8

MptGGUF by quarterturnUpdated 2024-07-25
Download on Hugging Face
Parameters30B
Context8K
Layers48
Architecturempt
Smallest quant31.8 GB
Quick answer

mpt 30b chat q8 needs about 43.6 GB of memory at its main file (a 31.8 GB file) with an 8K context window, so it fits on a 48 GB GPU.

mpt 30b chat q8 is a 30B-parameter Mpt model in GGUF format, quantized by quarterturn. Its trained context length is 8K tokens. The repository has 1 quant file, from 31.8 GB to 31.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—31.8 GB (3 parts) 43.6 GB
Too big Get file →

What GPU do you need for mpt 30b chat q8?

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 the main file (31.8 GB file, about 43.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturempt
Parameters30B
Layers48
Trained context8,192 tokens
KV cache (fp16)1344 KB per token

Source

Quantized byquarterturn
FamilyMpt
Downloads (HF)5
Last updated2024-07-25

Frequently asked questions about mpt 30b chat q8

How much VRAM does mpt 30b chat q8 need?

About 43.6 GB at its main file with an 8K context window. That is the 31.8 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 mpt 30b chat q8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 43.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mpt 30b chat q8 GGUF?

It depends on the quant: file is 31.8 GB.

What context length does mpt 30b chat q8 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 11.3 GB at 8K and 11.3 GB at 8K.

Where can I download mpt 30b chat q8 GGUF?

The files are on Hugging Face in the quarterturn/mpt-30b-chat-q8-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 mpt 30b chat q8 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Mpt models

All Mpt →

Other medium models

All medium models →