GE

Gemma 3n E4B It Android Control 84k

GemmaGGUF by mradermacherUpdated 2026-10-17
Download on Hugging Face
Parameters6.87B
Context32K
Layers35
Architecturegemma3n
Smallest quant3.9 GB
Quick answer

Gemma 3n E4B It Android Control 84k needs about 5.9 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.9 GB (Q2_K) to 13.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Gemma 3n E4B It Android Control 84k – fine‑tuned for mobile UI actions

Gemma 3n E4B It Android Control 84k is a 6.87B‑parameter model fine‑tuned with LoRA for Android UI control tasks. It supports vision and can process up to 32768 context tokens. The model is available as GGUF files for efficient inference.

Good at

  • Android UI control
  • Vision‑based instruction following
  • Low‑rank adaptation tasks

Limits

  • Limited to LoRA fine‑tuned tasks
  • Requires GGUF quant files for deployment

Best for

  • Mobile UI automation scripts
  • Android app testing
  • Instruction‑driven UI navigation

Who it’s for. Developers building automated Android UI agents, QA engineers, or researchers needing a lightweight model for UI control.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.9 GB 5.0 GB
Fits Get file →
Q3_K_S4.2 GB 5.3 GB
Fits Get file →
Q3_K_M4.4 GB 5.4 GB
Fits Get file →
Q3_K_L4.5 GB 5.6 GB
Fits Get file →
IQ4_XS4.6 GB 5.7 GB
Fits Get file →
Q4_K_S4.7 GB 5.8 GB
Fits Get file →
Q4_K_M4.8 GB 5.9 GB
Fits Get file →
Q5_K_S5.2 GB 6.3 GB
Fits Get file →
Q5_K_M5.3 GB 6.3 GB
Fits Get file →
Q6_K5.7 GB 6.8 GB
Fits Get file →
Q8_07.4 GB 8.4 GB
Too big Get file →
F1613.7 GB 14.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 5.9 GB memory at 8k context) or Q3_K_M (5.4 GB). For 12 GB VRAM, Q5_K_M (6.3 GB) or Q6_K (6.8 GB) provide a balance of size and performance. Larger VRAM allows Q8_0 (8.4 GB).

What GPU do you need for Gemma 3n E4B It Android Control 84k?

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: the best quant that fits is Q4_K_M (4.8 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.4 GB file, about 8.4 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (13.7 GB file, about 14.8 GB in use).

Which Gemma 3n E4B It Android Control 84k quant should you choose?

Q4_K_M is the usual starting point for Gemma 3n E4B It Android Control 84k: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 7.4 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.9 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

Architecturegemma3n
Parameters6.87B
Layers35
Trained context32,768 tokens
KV cache (fp16)70 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)582
Last updated2026-10-17

Frequently asked questions about Gemma 3n E4B It Android Control 84k

How much VRAM does Gemma 3n E4B It Android Control 84k need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.8 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 3n E4B It Android Control 84k on an 8 GB GPU?

Yes, with Q6_K: the 5.7 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 3n E4B It Android Control 84k GGUF?

It depends on the quant: Q2_K is 3.9 GB, Q3_K_S is 4.2 GB, Q3_K_M is 4.4 GB, Q3_K_L is 4.5 GB, IQ4_XS is 4.6 GB, Q4_K_S is 4.7 GB and 6 more.

What context length does Gemma 3n E4B It Android Control 84k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Gemma 3n E4B It Android Control 84k GGUF?

The files are on Hugging Face in the mradermacher/gemma-3n-E4B-it-Android-Control-84k-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 3n E4B It Android Control 84k use?

Hugging Face lists the license as gemma. 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, with Q4_K_M or Q3_K_M quantizations the estimated memory is below 8 GB at 8k context.

Does it support vision?

Yes, the model has detected vision abilities and includes a vision tower.

What license does it use?

The model is released under the gemma license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →