Yes — Gemma 4 E4B (4B) runs at 92 tok/s on M5 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.3s. Google's 4B PLE model with multimodal capabilities and outstanding speed.
Want to run Gemma 4 E4B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Gemma 4 E4B on M5 Pro using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →
| Metric | Value |
|---|---|
| Tokens per second | 92 tok/s |
| Time to first token | 0.3s |
| Quantization | Q4_K_M |
| Minimum RAM | 24 GB |
| Recommended engine | Ollama |
| Parameters | 4B |
| Benchmark date | 2026-04 |
Q4_K_M 4B Ollama M5 Pro
The recommended engine for Gemma 4 E4B on M5 Pro is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 128 tok/s | 0.2s | 128 GB | MLX |
| M4 Pro | 78 tok/s | 0.3s | 24 GB | MLX |
| M3 | 62 tok/s | 0.4s | 16 GB | Ollama |
| M1 | 42 tok/s | 0.6s | 8 GB | Ollama |
To run Gemma 4 E4B on M5 Pro you need:
Gemma 4 E4B needs about 24 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.
See how Gemma 4 E4B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard