GE

gemma 4 31B it heretic QAT For Edge 16G

GemmaGGUF by SC117Updated 2026-10-03
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant12.3 GB
Quick answer

gemma 4 31B it heretic QAT For Edge 16G needs about 46.5 GB of memory at Q3_K_S (a 13.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 12.3 GB (Q2_K_L) to 61.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B it Heretic QAT for Edge 16G

Gemma 4 31B it Heretic QAT is a 30.7B parameter model optimized with Quantization-Aware Training. It supports coding, reasoning, tools, and vision. The model offers a 262144 token context window and is released under Apache‑2.0.

Good at

  • Coding
  • Reasoning
  • Vision

Limits

  • Requires 16GB VRAM for Q2_K_L
  • Limited arithmetic accuracy
  • Repetition loops possible

Best for

  • Edge inference on 16GB GPUs
  • Multimodal text‑image tasks
  • Instruction‑tuned applications

Who it’s for. Developers needing a large multimodal model that fits within 16GB VRAM. Researchers exploring extreme quantization for edge deployment may also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_L12.3 GB 45.0 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
F1661.4 GB 94.1 GB
Too big Get file →

For 16GB VRAM, use Q2_K_L (12.26 GB, ~45 GB memory at 8k context). If more VRAM is available, Q3_K_S (13.76 GB, ~46.5 GB) offers higher precision. F16 (61.41 GB) requires large memory and is not suitable for 16GB GPUs.

What GPU do you need for gemma 4 31B it heretic QAT For Edge 16G?

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 Q3_K_S (13.8 GB file, about 46.5 GB in use).

Which gemma 4 31B it heretic QAT For Edge 16G quant should you choose?

Q3_K_S (13.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q2_K_L at 12.3 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 bySC117
FamilyGemma
Licenseapache-2.0
Downloads (HF)621
Last updated2026-10-03

Frequently asked questions about gemma 4 31B it heretic QAT For Edge 16G

How much VRAM does gemma 4 31B it heretic QAT For Edge 16G need?

About 46.5 GB at Q3_K_S with an 8K context window. That is the 13.8 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 4 31B it heretic QAT For Edge 16G on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 45.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 31B it heretic QAT For Edge 16G GGUF?

It depends on the quant: Q2_K_L is 12.3 GB, Q3_K_S is 13.8 GB, F16 is 61.4 GB.

What context length does gemma 4 31B it heretic QAT For Edge 16G 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 heretic QAT For Edge 16G GGUF?

The files are on Hugging Face in the SC117/gemma-4-31B-it-heretic-QAT-For-Edge-16G-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 heretic QAT For Edge 16G 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 8GB VRAM?

No. The Q2_K_L quantization requires 16GB VRAM. Smaller VRAM configurations are not supported.

What precision does Q2_K_L use?

Q2_K_L uses Q2_K for the body and Q8_0 for embeddings and output.

Is the model open source?

Yes, it is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-31B-it-qat-q4_0-unquantized-heretic

Similar models

Browse all →

More from SC117

All by SC117 →

More Gemma models

All Gemma →

Other medium models

All medium models →