GE

Soichi gemma4 31B FT

GemmaGGUF by soichi1208Updated 2026-06-01
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant11.9 GB
Quick answer

Soichi gemma4 31B FT 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 2 quants, from 11.9 GB (Q2_K) to 18.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Soichi gemma4 31B FT is a 30.7B-parameter Gemma model in GGUF format, quantized by soichi1208. Its trained context length is 256K tokens. The repository has 2 quant files, from 11.9 GB (Q2_K) to 18.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.9 GB 44.6 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →

What GPU do you need for Soichi gemma4 31B FT?

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 Q2_K (11.9 GB file, about 44.6 GB in use).

Which Soichi gemma4 31B FT quant should you choose?

Q4_K_M is the usual starting point for Soichi gemma4 31B FT: it balances file size and quality well. Here it is a 18.7 GB file.

If memory is tight, the smallest file is Q2_K at 11.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bysoichi1208
FamilyGemma
Licenseapache-2.0
Downloads (HF)27
Last updated2026-06-01

Frequently asked questions about Soichi gemma4 31B FT

How much VRAM does Soichi gemma4 31B FT 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 Soichi gemma4 31B FT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Soichi gemma4 31B FT GGUF?

It depends on the quant: Q2_K is 11.9 GB, Q4_K_M is 18.7 GB.

What context length does Soichi gemma4 31B FT 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 Soichi gemma4 31B FT GGUF?

The files are on Hugging Face in the soichi1208/Soichi-gemma4-31B-FT repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Soichi gemma4 31B FT 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 soichi1208

All by soichi1208 →

More Gemma models

All Gemma →

Other medium models

All medium models →