GE

Edge 4B TELL

GemmaGGUF by ginigen-aiUpdated 2026-09-19
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant5.2 GB
Quick answer

Edge 4B TELL needs about 7.1 GB of memory at Q4_0 (a 5.2 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.

Edge 4B TELL – a lightweight Gemma 4 model for on‑device inference

Edge 4B TELL is a 7.46 billion‑parameter Gemma 4 model quantized to Q4_0. It supports reasoning, tools, and vision. The model is released under Apache‑2.0 and is available as a GGUF file.

Good at

  • Reasoning tasks
  • Tool usage
  • Vision input

Limits

  • No audio support
  • No large context beyond 131072 tokens
  • Requires Q4_0 quantized file

Best for

  • Mobile disaster‑response apps
  • On‑device text generation
  • Low‑latency vision queries

Who it’s for. Developers building offline, device‑side AI applications that need a small, open‑source model with vision and reasoning capabilities. The model is suitable for Android apps that must operate without network access.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_05.2 GB 7.1 GB
Fits Get file →

For a device with 8 GB VRAM, the Q4_0 GGUF file (5.15 GB) will use approximately 7.1 GB of VRAM at 8 k context. If the device has less VRAM, consider a higher‑quantization model not listed here. The memory estimate is approximate.

What GPU do you need for Edge 4B TELL?

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 Q4_0 (5.2 GB file, about 7.1 GB in use).

Which Edge 4B TELL quant should you choose?

Q4_0 (5.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byginigen-ai
FamilyGemma
Licenseapache-2.0
Downloads (HF)563
Last updated2026-09-19

Frequently asked questions about Edge 4B TELL

How much VRAM does Edge 4B TELL need?

About 7.1 GB at Q4_0 with an 8K context window. That is the 5.2 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 Edge 4B TELL on an 8 GB GPU?

Yes, with Q4_0: the 5.2 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Edge 4B TELL GGUF?

It depends on the quant: Q4_0 is 5.2 GB.

What context length does Edge 4B TELL 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 Edge 4B TELL GGUF?

The files are on Hugging Face in the ginigen-ai/Edge-4B-TELL repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Edge 4B TELL 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 Edge 4B TELL on a device with 8 GB VRAM?

Yes, the Q4_0 GGUF file uses about 7.1 GB of VRAM at 8 k context, fitting within 8 GB.

Does Edge 4B TELL support audio input?

No, audio support is available only on E2B, E4B, and 12B variants, not on this model.

Other GGUFs of gemma-4-E4B-it-qat-q4_0-gguf

Similar models

Browse all →

More Gemma models

All Gemma →

Other small models

All small models →