OP

OpenDolphinMaid 4x7b

OpendolphinmaidGGUF by Undi95Updated 2024-01-14
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant13.6 GB
Quick answer

OpenDolphinMaid 4x7b needs about 18.2 GB of memory at Q5_0 (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 13.6 GB (Q4_0) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

OpenDolphinMaid 4x7b is a 24.2B-parameter Opendolphinmaid model in GGUF format, quantized by Undi95. Its trained context length is 32K tokens. The repository has 3 quant files, from 13.6 GB (Q4_0) to 25.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_013.6 GB 15.2 GB
Too big Get file →
Q5_016.6 GB 18.2 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

What GPU do you need for OpenDolphinMaid 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: the best quant that fits is Q4_0 (13.6 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_0 (16.6 GB file, about 18.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which OpenDolphinMaid 4x7b quant should you choose?

Q5_0 (16.6 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.

If memory is tight, the smallest file is Q4_0 at 13.6 GB, with the quality trade-offs that come with fewer bits. 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byUndi95
Downloads (HF)28
Last updated2024-01-14

Frequently asked questions about OpenDolphinMaid 4x7b

How much VRAM does OpenDolphinMaid 4x7b need?

About 18.2 GB at Q5_0 with an 8K context window. That is the 16.6 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 OpenDolphinMaid 4x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OpenDolphinMaid 4x7b GGUF?

It depends on the quant: Q4_0 is 13.6 GB, Q5_0 is 16.6 GB, Q8_0 is 25.7 GB.

What context length does OpenDolphinMaid 4x7b 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 OpenDolphinMaid 4x7b GGUF?

The files are on Hugging Face in the Undi95/OpenDolphinMaid-4x7b-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 OpenDolphinMaid 4x7b use?

Hugging Face lists the license as cc-by-nc-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 from Undi95

All by Undi95 →

More Opendolphinmaid models

All Opendolphinmaid →

Other medium models

All medium models →