LU

G4 LuneLight 31B Pos r2 c24

LunelightGGUF by ApocalypsePartyUpdated 2026-10-31
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant25.2 GB
Quick answer

G4 LuneLight 31B Pos r2 c24 needs about 57.9 GB of memory at Q6_K (a 25.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 25.2 GB (Q6_K) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

G4 LuneLight 31B Pos r2 c24 is a 30.7B-parameter Lunelight model in GGUF format, quantized by ApocalypseParty. Its trained context length is 256K tokens. The repository has 2 quant files, from 25.2 GB (Q6_K) to 32.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K25.2 GB 57.9 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →

What GPU do you need for G4 LuneLight 31B Pos r2 c24?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which G4 LuneLight 31B Pos r2 c24 quant should you choose?

Q6_K (25.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byApocalypseParty
FamilyLunelight
Downloads (HF)174
Last updated2026-10-31

Frequently asked questions about G4 LuneLight 31B Pos r2 c24

How much VRAM does G4 LuneLight 31B Pos r2 c24 need?

About 57.9 GB at Q6_K with an 8K context window. That is the 25.2 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 G4 LuneLight 31B Pos r2 c24 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 57.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of G4 LuneLight 31B Pos r2 c24 GGUF?

It depends on the quant: Q6_K is 25.2 GB, Q8_0 is 32.6 GB.

What context length does G4 LuneLight 31B Pos r2 c24 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download G4 LuneLight 31B Pos r2 c24 GGUF?

The files are on Hugging Face in the ApocalypseParty/G4-LuneLight-31B-Pos-r2-c24-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from ApocalypseParty

All by ApocalypseParty →

More Lunelight models

All Lunelight →

Other medium models

All medium models →