GE

gemma 4 31B it DASHQ Q2

GemmaGGUF by jkim96Updated 2026-10-02
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant8.8 GB
Quick answer

gemma 4 31B it DASHQ Q2 needs about 42.7 GB of memory at IQ2_XS (a 10.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 8.8 GB (IQ2_XXS) to 12.0 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B instruction-tuned model in 2‑bit DASH‑Q quantizations

Gemma 4 31B it is a 30.7B parameter instruction‑tuned model from Google DeepMind. It is available in several 2‑bit quantizations for local deployment. The model supports a 262144 token context window and is released under Apache 2.0.

Good at

  • Large‑scale text generation
  • Reasoning tasks
  • Coding and function‑calling

Limits

  • No vision support in GGUF files
  • Requires high VRAM for larger quants
  • Context limited to 262144 tokens

Best for

  • Deploying on high‑end laptops
  • Running on servers with 8–16 GB VRAM
  • Fine‑tuning for specific instruction sets

Who it’s for. Developers and researchers needing a large instruction‑tuned model that can run locally with 2‑bit quantization. The model is suitable for applications that require extensive context and reasoning capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS8.8 GB 41.5 GB
Too big Get file →
IQ2_XS10.0 GB 42.7 GB
Too big Get file →
IQ2_M11.1 GB 43.8 GB
Too big Get file →
Q2_K_XL12.0 GB 44.7 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (8.82 GB file, ~41.5 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (10.03 GB file, ~42.7 GB memory). For 16 GB VRAM, IQ2_M (11.08 GB file, ~43.8 GB memory). The Q2_K_XL quant (11.98 GB file, ~44.7 GB memory) requires the largest memory budget.

What GPU do you need for gemma 4 31B it DASHQ Q2?

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_XL (12.0 GB file, about 44.7 GB in use).

Which gemma 4 31B it DASHQ Q2 quant should you choose?

IQ2_XS (10.0 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ2_XXS at 8.8 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 byjkim96
FamilyGemma
Licenseapache-2.0
Downloads (HF)221
Last updated2026-10-02

Frequently asked questions about gemma 4 31B it DASHQ Q2

How much VRAM does gemma 4 31B it DASHQ Q2 need?

About 42.7 GB at IQ2_XS with an 8K context window. That is the 10.0 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 DASHQ Q2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 31B it DASHQ Q2 GGUF?

It depends on the quant: IQ2_XXS is 8.8 GB, IQ2_XS is 10.0 GB, IQ2_M is 11.1 GB, Q2_K_XL is 12.0 GB.

What context length does gemma 4 31B it DASHQ Q2 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 it DASHQ Q2 GGUF?

The files are on Hugging Face in the jkim96/gemma-4-31B-it-DASHQ-Q2-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 DASHQ Q2 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.

Can I run this model on 8 GB VRAM?

Yes, the IQ2_XXS quant uses 8.82 GB file size and estimates about 41.5 GB memory at 8 k context, which fits on 8 GB VRAM with efficient batching.

Does the GGUF version support image input?

No, the GGUF files contain only text weights; the vision tower is not included.

What license applies to this model?

The model is released under the Apache 2.0 license, inherited from the base google/gemma-4-31B-it model.

Other GGUFs of gemma-4-31B-it

Similar models

Browse all →

More from jkim96

All by jkim96 →

More Gemma models

All Gemma →

Other medium models

All medium models →