GE

gemma 4 31B it EAGLE3 Speculator

GemmaGGUF by williamliaoUpdated 2026-06-14
Download on Hugging Face
Parameters2.24B
Context256K
Layers1
Architectureeagle3
Smallest quant1.3 GB
Quick answer

gemma 4 31B it EAGLE3 Speculator needs about 2.0 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.3 GB (Q4_K_M) to 4.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

gemma 4 31B it EAGLE3 Speculator is a 2.24B-parameter Gemma model in GGUF format, quantized by williamliao. Its trained context length is 256K tokens. The repository has 3 quant files, from 1.3 GB (Q4_K_M) to 4.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.0 GB
Fits Get file →
Q8_02.4 GB 3.0 GB
Fits Get file →
F164.5 GB 5.1 GB
Fits Get file →

What GPU do you need for gemma 4 31B it EAGLE3 Speculator?

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: the best quant that fits is Q8_0 (2.4 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.5 GB file, about 5.1 GB in use).

Which gemma 4 31B it EAGLE3 Speculator quant should you choose?

Q4_K_M is the usual starting point for gemma 4 31B it EAGLE3 Speculator: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.4 GB, about 1.8 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureeagle3
Parameters2.24B
Layers1
Trained context262,144 tokens
KV cache (fp16)16 KB per token

Source

Quantized bywilliamliao
FamilyGemma
Licenseapache-2.0
Downloads (HF)184
Last updated2026-06-14

Frequently asked questions about gemma 4 31B it EAGLE3 Speculator

How much VRAM does gemma 4 31B it EAGLE3 Speculator need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 1.3 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 it EAGLE3 Speculator on an 8 GB GPU?

Yes, with F16: the 4.5 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma 4 31B it EAGLE3 Speculator GGUF?

It depends on the quant: Q4_K_M is 1.3 GB, Q8_0 is 2.4 GB, F16 is 4.5 GB.

What context length does gemma 4 31B it EAGLE3 Speculator support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.5 GB at 32K.

Where can I download gemma 4 31B it EAGLE3 Speculator GGUF?

The files are on Hugging Face in the williamliao/gemma-4-31B-it-EAGLE3-Speculator-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 4 31B it EAGLE3 Speculator 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.

Other GGUFs of gemma-4-31B-it-speculator.eagle3

Similar models

Browse all →

More from williamliao

All by williamliao →

More Gemma models

All Gemma →

Other tiny models

All tiny models →