MO

Moonlight 16B FLOE 01

MoonlightGGUF by ColdTensorUpdated 2026-11-12
Download on Hugging Face
Parameters12.4B
Context8K
Layers27
Architecturedeepseek2
Smallest quant6.7 GB
Quick answer

Moonlight 16B FLOE 01 needs about 7.7 GB of memory at its main file (a 6.7 GB file) with an 8K context window, so it fits on a 8 GB GPU.

Moonlight 16B FLOE 01 is a 12.4B-parameter Moonlight model in GGUF format, quantized by ColdTensor. Its trained context length is 8K tokens. The repository has 1 quant file, from 6.7 GB to 6.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.7 GB 7.7 GB
Tight Get file →

What GPU do you need for Moonlight 16B FLOE 01?

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: the best quant that fits is the main file (6.7 GB file, about 7.7 GB in use).

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters12.4B (approximate, mixture of experts)
Layers27
Trained context8,192 tokens
KV cache (fp16)57 KB per token

Source

Quantized byColdTensor
FamilyMoonlight
Licensemit
Downloads (HF)115
Last updated2026-11-12

Frequently asked questions about Moonlight 16B FLOE 01

How much VRAM does Moonlight 16B FLOE 01 need?

About 7.7 GB at its main file with an 8K context window. That is the 6.7 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 Moonlight 16B FLOE 01 on an 8 GB GPU?

Yes, with the smaller files: the 6.7 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Moonlight 16B FLOE 01 GGUF?

It depends on the quant: file is 6.7 GB.

What context length does Moonlight 16B FLOE 01 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.

Where can I download Moonlight 16B FLOE 01 GGUF?

The files are on Hugging Face in the ColdTensor/Moonlight-16B-FLOE-01-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 Moonlight 16B FLOE 01 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Moonlight-16B-A3B-Instruct

Similar models

Browse all →

More Moonlight models

All Moonlight →

Other medium models

All medium models →