GE

GEMMA 31B LIBERADO

GemmaGGUF by HALO117MCUpdated 2026-10-06
Download on Hugging Face
Parameters30.7B
Context256K
Layers—
Architecturegemma4
Smallest quant13.8 GB
Quick answer

GEMMA 31B LIBERADO needs about 25.0 GB of memory at Q5_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 13.8 GB (Q3_K_S) to 61.4 GB (BF16).

GEMMA 31B LIBERADO is a 30.7B-parameter Gemma model in GGUF format, quantized by HALO117MC. Its trained context length is 256K tokens. The repository has 6 quant files, from 13.8 GB (Q3_K_S) to 61.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S13.8 GB 15.9 GB
Too big Get file →
IQ4_XS16.9 GB 19.4 GB
Too big Get file →
Q5_K_M21.8 GB 25.0 GB
Too big Get file →
Q6_K25.5 GB 29.1 GB
Too big Get file →
Q8_032.6 GB 37.1 GB
Too big Get file →
BF1661.4 GB 69.3 GB
Too big Get file →

What GPU do you need for GEMMA 31B LIBERADO?

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: 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: the best quant that fits is Q3_K_S (13.8 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (16.9 GB file, about 19.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (25.5 GB file, about 29.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.6 GB file, about 37.1 GB in use).

Which GEMMA 31B LIBERADO quant should you choose?

Q5_K_M (21.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q3_K_S at 13.8 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
Trained context262,144 tokens

Source

Quantized byHALO117MC
FamilyGemma
Licensegemma
Downloads (HF)11
Last updated2026-10-06

Frequently asked questions about GEMMA 31B LIBERADO

How much VRAM does GEMMA 31B LIBERADO need?

About 25.0 GB at Q5_K_M with an 8K context window. That is the 21.8 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 GEMMA 31B LIBERADO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GEMMA 31B LIBERADO GGUF?

It depends on the quant: Q3_K_S is 13.8 GB, IQ4_XS is 16.9 GB, Q5_K_M is 21.8 GB, Q6_K is 25.5 GB, Q8_0 is 32.6 GB, BF16 is 61.4 GB.

What context length does GEMMA 31B LIBERADO support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download GEMMA 31B LIBERADO GGUF?

The files are on Hugging Face in the HALO117MC/GEMMA_31B_LIBERADO-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 GEMMA 31B LIBERADO 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.

Similar models

Browse all →

More from HALO117MC

All by HALO117MC →

More Gemma models

All Gemma →

Other medium models

All medium models →