GE

gemma 4 31b instruct lmk

GemmaGGUF by lm-kitUpdated 2026-10-10
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant61.4 GB
Quick answer

gemma 4 31b instruct lmk needs about 94.1 GB of memory at F16 (a 61.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

gemma 4 31b instruct lmk is a 30.7B-parameter Gemma model in GGUF format, quantized by lm-kit. Its trained context length is 256K tokens. The repository has 1 quant file, from 61.4 GB (F16) to 61.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1661.4 GB 94.1 GB
Too big Get file →

What GPU do you need for gemma 4 31b instruct lmk?

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 gemma 4 31b instruct lmk quant should you choose?

F16 (61.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 bylm-kit
FamilyGemma
Licenseapache-2.0
Downloads (HF)60
Last updated2026-10-10

Frequently asked questions about gemma 4 31b instruct lmk

How much VRAM does gemma 4 31b instruct lmk need?

About 94.1 GB at F16 with an 8K context window. That is the 61.4 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 4 31b instruct lmk on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 94.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 31b instruct lmk GGUF?

It depends on the quant: F16 is 61.4 GB.

What context length does gemma 4 31b instruct lmk 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 gemma 4 31b instruct lmk GGUF?

The files are on Hugging Face in the lm-kit/gemma-4-31b-instruct-lmk 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 4 31b instruct lmk use?

Hugging Face lists the license as apache-2.0. 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 lm-kit

All by lm-kit →

More Gemma models

All Gemma →

Other medium models

All medium models →