text model · Gemma · macOS
Can I run Gemma 3n E4B on Apple M4 Max (128GB)?
Yes. Gemma 3n E4B runs on Apple M4 Max (128GB) at Q4_K_M (~5.7 GB of ~96 GB usable).
Runs at Q4_K_M using ~5.7 GB of ~96 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Apple M4 Max (128GB) leaves ~90.3 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~5.7 GB
- Usable on device
- ~96 GB
- Device memory
- 128 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~145 W
- Electricity / 1M tokens
- ~$0.06
- Pays for itself after
- ~7,952M tok
At ~$0.15/kWh and the estimated ~103 tok/s, a million generated tokens costs about $0.06 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$3,499 Apple M4 Max (128GB) pays for itself after roughly 7,952 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run gemma3n:e4b llama-cli -hf unsloth/gemma-3n-E4B-it-GGUF:Q4_K_M lms get unsloth/gemma-3n-E4B-it-GGUF - Parameters
- 8B
- Q4_K_M size
- 4.23 GB
- Q8_0 size
- 6.85 GB
- Context
- 32k
- Ollama tag
- gemma3n:e4b
- Memory
- 128 GB unified
- Usable for weights
- ~96 GB
- Power draw
- ~145 W
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run Gemma 3n E4B on other hardware
FAQ
Can Apple M4 Max (128GB) run Gemma 3n E4B?
Yes. Gemma 3n E4B runs on Apple M4 Max (128GB) at Q4_K_M (~5.7 GB of ~96 GB usable).
How much memory does Gemma 3n E4B need?
Apple M4 Max (128GB) has room to spare. At Q4_K_M the weights are ~4.23 GB; with KV cache and runtime overhead, budget ~5.7 GB at a 4k context.
What is the best tool to run Gemma 3n E4B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/gemma-3n-e4b/apple-m4-max-128gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.