GE

Merged Gemma 3n

GemmaGGUF by gigwegbeUpdated 2025-08-03
Download on Hugging Face
Parameters4.46B
Context32K
Layers30
Architecturegemma3n
Smallest quant1.9 GB
Quick answer

Merged Gemma 3n needs about 3.8 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.9 GB (Q2_K) to 8.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.

Merged Gemma 3n is a 4.46B-parameter Gemma model in GGUF format, quantized by gigwegbe. Its trained context length is 32K tokens. The repository has 7 quant files, from 1.9 GB (Q2_K) to 8.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 2.9 GB
Fits Get file →
Q4_K_M2.8 GB 3.8 GB
Fits Get file →
—4.7 GB 5.7 GB
Fits Get file →
—5.5 GB 6.5 GB
Fits Get file →
—5.6 GB 6.6 GB
Fits Get file →
BF168.9 GB 9.9 GB
Too big Get file →
F168.9 GB 9.9 GB
Too big Get file →

What GPU do you need for Merged Gemma 3n?

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 Q4_K_M (2.8 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.6 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.9 GB file, about 9.9 GB in use).

Which Merged Gemma 3n quant should you choose?

Q4_K_M is the usual starting point for Merged Gemma 3n: it balances file size and quality well. Here it is a 2.8 GB file.

If memory is tight, the smallest file is Q2_K at 1.9 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
Parameters4.46B
Layers30
Trained context32,768 tokens
KV cache (fp16)60 KB per token

Source

Quantized bygigwegbe
FamilyGemma
Downloads (HF)66
Last updated2025-08-03

Frequently asked questions about Merged Gemma 3n

How much VRAM does Merged Gemma 3n need?

About 3.8 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Merged Gemma 3n on an 8 GB GPU?

Yes, with the smaller files: the 5.6 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 Merged Gemma 3n GGUF?

It depends on the quant: Q2_K is 1.9 GB, Q4_K_M is 2.8 GB, file is 4.7 GB, file is 5.5 GB, file is 5.6 GB, BF16 is 8.9 GB and 1 more.

What context length does Merged Gemma 3n support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.

Where can I download Merged Gemma 3n GGUF?

The files are on Hugging Face in the gigwegbe/gemma3n-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Gemma models

All Gemma →

Other small models

All small models →