GE

gemma 4 OBLITERATED IMATRIX IQ3 M

GemmaGGUF by levanellUpdated 2026-05-06
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant4.7 GB
Quick answer

gemma 4 OBLITERATED IMATRIX IQ3 M needs about 6.6 GB of memory at IQ3_M (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

gemma 4 OBLITERATED IMATRIX IQ3 M is a 7.52B-parameter Gemma model in GGUF format, quantized by levanell. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.7 GB (IQ3_M) to 4.7 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M4.7 GB 6.6 GB
Fits Get file →

What GPU do you need for gemma 4 OBLITERATED IMATRIX IQ3 M?

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: the best quant that fits is IQ3_M (4.7 GB file, about 6.6 GB in use).

Which gemma 4 OBLITERATED IMATRIX IQ3 M quant should you choose?

IQ3_M (4.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bylevanell
FamilyGemma
Licenseapache-2.0
Downloads (HF)11
Last updated2026-05-06

Frequently asked questions about gemma 4 OBLITERATED IMATRIX IQ3 M

How much VRAM does gemma 4 OBLITERATED IMATRIX IQ3 M need?

About 6.6 GB at IQ3_M with an 8K context window. That is the 4.7 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 gemma 4 OBLITERATED IMATRIX IQ3 M on an 8 GB GPU?

Yes, with IQ3_M: the 4.7 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma 4 OBLITERATED IMATRIX IQ3 M GGUF?

It depends on the quant: IQ3_M is 4.7 GB.

What context length does gemma 4 OBLITERATED IMATRIX IQ3 M support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download gemma 4 OBLITERATED IMATRIX IQ3 M GGUF?

The files are on Hugging Face in the levanell/gemma-4-OBLITERATED-IMATRIX-IQ3_M 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 OBLITERATED IMATRIX IQ3 M 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-E4B-it-OBLITERATED

Similar models

Browse all →

More from levanell

All by levanell →

More Gemma models

All Gemma →

Other small models

All small models →