LI

Lilith 31B v1.0

LilithGGUF by darthcrawlUpdated 2026-07-26
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant14.4 GB
Quick answer

Lilith 31B v1.0 needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 14.4 GB (IQ3_M) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Lilith 31B v1.0 is a 30.7B-parameter Lilith model in GGUF format, quantized by darthcrawl. Its trained context length is 256K tokens. The repository has 7 quant files, from 14.4 GB (IQ3_M) to 32.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M14.4 GB 47.1 GB
Too big Get file →
Q3_K_M15.3 GB 48.0 GB
Too big Get file →
IQ4_XS16.7 GB 49.4 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →
Q5_K_M21.8 GB 54.6 GB
Too big Get file →
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 Lilith 31B v1.0?

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: the best quant that fits is Q3_K_M (15.3 GB file, about 48.0 GB in use).

Which Lilith 31B v1.0 quant should you choose?

Q4_K_M is the usual starting point for Lilith 31B v1.0: it balances file size and quality well. Here it is a 18.7 GB file.

The Q8_0 file is 32.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ3_M at 14.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 bydarthcrawl
FamilyLilith
Licensegemma
Downloads (HF)391
Last updated2026-07-26

Frequently asked questions about Lilith 31B v1.0

How much VRAM does Lilith 31B v1.0 need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Lilith 31B v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lilith 31B v1.0 GGUF?

It depends on the quant: IQ3_M is 14.4 GB, Q3_K_M is 15.3 GB, IQ4_XS is 16.7 GB, Q4_K_M is 18.7 GB, Q5_K_M is 21.8 GB, Q6_K is 25.2 GB and 1 more.

What context length does Lilith 31B v1.0 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 Lilith 31B v1.0 GGUF?

The files are on Hugging Face in the darthcrawl/Lilith-31B-v1.0-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 Lilith 31B v1.0 use?

Hugging Face lists the license as gemma. 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 Lilith-31B-v1.0

Similar models

Browse all →

More from darthcrawl

All by darthcrawl →

More Lilith models

All Lilith →

Other medium models

All medium models →