Download Gemma 4 E4B GGUF
Gemma 4 E4B is an 8B-parameter multimodal model. Google's official QAT model card publishes a ready-to-deploy GGUF Q4_0 checkpoint; this page shows the verified source, the local runtime commands, and the hardware considerations that affect memory use.
GGUF is the format used by Ollama, llama.cpp, LM Studio and KoboldCpp. All files are published under the Apache 2.0 license — free for personal and commercial use, no Hugging Face account required.
Gemma 4 E4B GGUF File Sizes & Filenames
The table below lists community quantization files from Unsloth. For the canonical Google QAT Q4_0 checkpoint, use Google's model card linked in the source section.
| Quant | Filename | Size | Min VRAM |
|---|---|---|---|
| Q4_K_M | gemma-4-E4B-it-Q4_K_M.gguf | 4.98 GB | ~6 GB |
| Q5_K_M | gemma-4-E4B-it-Q5_K_M.gguf | 5.48 GB | ~7 GB |
| Q8_0 | gemma-4-E4B-it-Q8_0.gguf | 8.19 GB | ~10 GB |
| BF16 | gemma-4-E4B-it-BF16.gguf | 15.1 GB | ~17 GB |
Community quantization sizes are from the linked Unsloth repository. For the canonical Google QAT Q4_0 checkpoint, use Google's model card linked in the source section: unsloth/gemma-4-E4B-it-GGUF Official Google E4B QAT Q4_0 model card
How to Download Gemma 4 E4B GGUF
Hugging Face CLI
Download a single quant file directly (recommended — avoids pulling the whole repo):
pip install huggingface_hub
# Recommended Q4_K_M build (4.98 GB)
huggingface-cli download unsloth/gemma-4-E4B-it-GGUF \
--include "gemma-4-E4B-it-Q4_K_M.gguf"Ollama
One command to pull and run — Ollama auto-selects an optimized quant:
ollama pull gemma4:e4b
ollama run gemma4:e4bllama.cpp
Run straight from the Hugging Face repo with llama.cpp's built-in downloader:
./llama-cli -hf unsloth/gemma-4-E4B-it-GGUF:Q4_K_MFAQ
Which Gemma 4 E4B GGUF quant should I download?
Q4_K_M (4.98 GB) is the best default — it keeps ~93–95% of full quality while staying small enough for mainstream 8–16 GB GPUs. Choose Q5_K_M or Q8_0 if you have spare VRAM and want higher fidelity, or BF16 for full precision.
What is the file size of Gemma 4 E4B GGUF?
The Q4_K_M build is 4.98 GB. Larger quants range up the table to BF16. See the file-size table above for every quant.
How do I run Gemma 4 E4B with Ollama?
Run `ollama pull gemma4:e4b` then `ollama run gemma4:e4b`. Ollama downloads an optimized GGUF automatically and sets up the chat template for you.
Can the Gemma 4 E4B GGUF run on CPU only?
Yes. GGUF with llama.cpp or Ollama runs on CPU, GPU, or a hybrid split. CPU-only works but is slower; offloading layers to even a modest GPU speeds it up significantly.
Do I need a Hugging Face account or license acceptance?
No. Gemma 4 is Apache 2.0 and the GGUF files are publicly downloadable without an account or gated access.
Looking for other Gemma 4 sizes?
Compare every variant (E2B, E4B, 26B MoE, 31B Dense) in all formats, or check hardware requirements before you download.