MO

Moonlight L3 15B v2.5 64k Q4 K S

MoonlightGGUF by hibikiassUpdated 2024-10-19
Download on Hugging Face
Parameters15B
Context64K
Layers64
Architecturellama
Smallest quant8.6 GB
Quick answer

Moonlight L3 15B v2.5 64k Q4 K S needs about 11.3 GB of memory at Q4_K_S (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Moonlight L3 15B v2.5 64k Q4 K S is a 15B-parameter Moonlight model in GGUF format, quantized by hibikiass. Its trained context length is 64K tokens. The repository has 1 quant file, from 8.6 GB (Q4_K_S) to 8.6 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S8.6 GB 11.3 GB
Too big Get file →

What GPU do you need for Moonlight L3 15B v2.5 64k Q4 K S?

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: the best quant that fits is Q4_K_S (8.6 GB file, about 11.3 GB in use).

Which Moonlight L3 15B v2.5 64k Q4 K S quant should you choose?

Q4_K_S (8.6 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

Architecturellama
Parameters15B
Layers64
Trained context65,536 tokens
KV cache (fp16)256 KB per token

Source

Quantized byhibikiass
FamilyMoonlight
Downloads (HF)7
Last updated2024-10-19

Frequently asked questions about Moonlight L3 15B v2.5 64k Q4 K S

How much VRAM does Moonlight L3 15B v2.5 64k Q4 K S need?

About 11.3 GB at Q4_K_S with an 8K context window. That is the 8.6 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 Moonlight L3 15B v2.5 64k Q4 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Moonlight L3 15B v2.5 64k Q4 K S GGUF?

It depends on the quant: Q4_K_S is 8.6 GB.

What context length does Moonlight L3 15B v2.5 64k Q4 K S support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Moonlight L3 15B v2.5 64k Q4 K S GGUF?

The files are on Hugging Face in the hibikiass/Moonlight-L3-15B-v2.5-64k-Q4_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Moonlight-L3-15B-v2.5-64k

Similar models

Browse all →

More from hibikiass

All by hibikiass →

More Moonlight models

All Moonlight →

Other medium models

All medium models →