GoogleGemma 3 4B on Apple M2 (16GB Unified)
M2 (16GB Unified) runs Gemma 3 4B at Q5_K_M — 9 tok/s. Usable on 16 GB VRAM — see full quantization options below.
Model Size
4.3B
Device VRAM
16 GB
Bandwidth
100 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Gemma 3 4B on Apple M2 (16GB Unified) at Q5_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 9 tok/s | – | ✓ Yes | Acceptable | estimated |
Notes
Q5_K_M
Conservative estimate anchored to existing Apple Silicon results. Memory bandwidth and quantization size are the primary inference limiters.
About Gemma 3 4B
Gemma 3 4B (4.3B) is a chat, coding model. Compact Gemma 3 model for chat and light coding on low-VRAM hardware.
View all Gemma 3 4B hardware options →About Apple M2 (16GB Unified)
Apple M2 (16GB Unified) has 16 GB at 100 GB/s. Available in MacBook Air 13" (2022), MacBook Air 15" (2023), MacBook Pro 13" (2022).
See all models Apple M2 (16GB Unified) can run →Estimate method: Conservative estimate anchored to m4-16gb with bandwidth scaling, quantization-size adjustment, and generation damping. Reference hardware source: github.com (2026-04-18)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.