GE

Gemma 4 12B it QAT Q5 K L MTP

GemmaGGUF by OliviaRossiUpdated 2026-10-05
Download on Hugging Face
Parameters11.9B
Context256K
Layers4
Architecturegemma4-assistant
Smallest quant0.5 GB
Quick answer

Gemma 4 12B it QAT Q5 K L MTP needs about 2.0 GB of memory at Q5_K_L (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q5_K_L) to 8.8 GB (Q5_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Gemma 4 12B it QAT Q5 K L MTP – multimodal, instruction‑tuned, QAT‑quantized

Gemma 4 12B it QAT Q5 K L MTP is a 11.9B parameter model from the Gemma family. It supports text, image, and audio input with a 262144 token context window. The model is released under Apache‑2.0 and includes a Multi‑Token Prediction drafter head.

Good at

  • Multimodal reasoning
  • Instruction following
  • Speculative decoding

Limits

  • No vision support without mmproj
  • Requires 8k context for memory estimates
  • No Mixture‑of‑Experts

Best for

  • Chat assistants
  • Code generation
  • Multimodal content creation

Who it’s for. Developers and researchers needing a compact, multimodal LLM that can run on consumer GPUs. The model is suitable for edge deployments and research prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_L0.5 GB 2.0 GB
Fits Get file →
Q5_K_L8.8 GB 10.4 GB
Too big Get file →

For 4‑8 GB VRAM, use the 0.47 GB Q5_K_L file which needs about 2 GB at 8k context. For 10 GB or more VRAM, the 8.79 GB Q5_K_L file is available and requires about 10.4 GB at 8k context. Memory estimates are approximate.

What GPU do you need for Gemma 4 12B it QAT Q5 K L MTP?

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 Q5_K_L (0.5 GB file, about 2.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_L (0.5 GB file, about 2.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_L (0.5 GB file, about 2.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_L (8.8 GB file, about 10.4 GB in use).

Which Gemma 4 12B it QAT Q5 K L MTP quant should you choose?

Q5_K_L (0.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4-assistant
Parameters11.9B
Layers4
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byOliviaRossi
FamilyGemma
Licenseapache-2.0
Downloads (HF)886
Last updated2026-10-05

Frequently asked questions about Gemma 4 12B it QAT Q5 K L MTP

How much VRAM does Gemma 4 12B it QAT Q5 K L MTP need?

About 2.0 GB at Q5_K_L with an 8K context window. That is the 0.5 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 12B it QAT Q5 K L MTP on an 8 GB GPU?

Yes, with Q5_K_L: the 0.5 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 12B it QAT Q5 K L MTP GGUF?

It depends on the quant: Q5_K_L is 0.5 GB, Q5_K_L is 8.8 GB.

What context length does Gemma 4 12B it QAT Q5 K L MTP support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Gemma 4 12B it QAT Q5 K L MTP GGUF?

The files are on Hugging Face in the OliviaRossi/Gemma-4-12B-it-QAT-Q5_K_L-MTP-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 12B it QAT Q5 K L MTP 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 0.47 GB Q5_K_L quantization requires about 2 GB at 8k context, fitting within 8 GB VRAM.

Does this model support vision?

Yes, it includes a Multimodal Projector (mmproj) for image and audio understanding.

What license does this model use?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-12B-it-qat-q4_0-unquantized

Similar models

Browse all →

More from OliviaRossi

All by OliviaRossi →

More Gemma models

All Gemma →

Other medium models

All medium models →