RA

ratchet moondream 2

RatchetGGUF by ratchet-communityUpdated 2024-06-21
Download on Hugging Face
Parameters1.87B
Context—
Layers—
Architecture—
Smallest quant2.4 GB
Quick answer

ratchet moondream 2 needs about 3.2 GB of memory at Q8_0 (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.4 GB (Q8_0) to 7.5 GB (F32).

ratchet moondream 2 is a 1.87B-parameter Ratchet model in GGUF format, quantized by ratchet-community. The repository has 2 quant files, from 2.4 GB (Q8_0) to 7.5 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.4 GB 3.2 GB
Fits Get file →
F327.5 GB 8.9 GB
Too big Get file →

What GPU do you need for ratchet moondream 2?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (7.5 GB file, about 8.9 GB in use).

Which ratchet moondream 2 quant should you choose?

Q8_0 (2.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters1.87B

Source

Quantized byratchet-community
FamilyRatchet
Licenseapache-2.0
Downloads (HF)135
Last updated2024-06-21

Frequently asked questions about ratchet moondream 2

How much VRAM does ratchet moondream 2 need?

About 3.2 GB at Q8_0 with an 8K context window. That is the 2.4 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 ratchet moondream 2 on an 8 GB GPU?

Yes, with Q8_0: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ratchet moondream 2 GGUF?

It depends on the quant: Q8_0 is 2.4 GB, F32 is 7.5 GB.

Where can I download ratchet moondream 2 GGUF?

The files are on Hugging Face in the ratchet-community/ratchet-moondream-2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ratchet moondream 2 use?

Hugging Face lists the license as apache-2.0. 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 Ratchet models

All Ratchet →

Other tiny models

All tiny models →