MP

mpt 30b instruct

MptGGUF by filipealmeidaUpdated 2023-10-05
Download on Hugging Face
Parameters30.3B
Context8K
Layers48
Architecturempt
Smallest quant17.2 GB
Quick answer

mpt 30b instruct needs about 28.9 GB of memory at Q4_0 (a 17.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 17.2 GB (Q4_0) to 32.2 GB (Q8_0).

mpt 30b instruct is a 30.3B-parameter Mpt model in GGUF format, quantized by filipealmeida. Its trained context length is 8K tokens. The repository has 2 quant files, from 17.2 GB (Q4_0) to 32.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_017.2 GB 28.9 GB
Too big Get file →
Q8_032.2 GB 44.0 GB
Too big Get file →

What GPU do you need for mpt 30b 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: 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: the best quant that fits is Q4_0 (17.2 GB file, about 28.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.2 GB file, about 44.0 GB in use).

Which mpt 30b instruct quant should you choose?

Q4_0 (17.2 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

Architecturempt
Parameters30.3B
Layers48
Trained context8,192 tokens
KV cache (fp16)1344 KB per token

Source

Quantized byfilipealmeida
FamilyMpt
Downloads (HF)146
Last updated2023-10-05

Frequently asked questions about mpt 30b instruct

How much VRAM does mpt 30b instruct need?

About 28.9 GB at Q4_0 with an 8K context window. That is the 17.2 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 instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mpt 30b instruct GGUF?

It depends on the quant: Q4_0 is 17.2 GB, Q8_0 is 32.2 GB.

What context length does mpt 30b instruct 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 instruct GGUF?

The files are on Hugging Face in the filipealmeida/mpt-30b-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 mpt 30b instruct use?

Hugging Face lists the license as cc-by-sa-3.0. 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 from filipealmeida

All by filipealmeida →

More Mpt models

All Mpt →

Other medium models

All medium models →