Qwen 3 30B A3B — Apple Silicon Benchmarks
Measured inference speed for Qwen 3 30B A3B across 2 Apple Silicon chips. Tokens per second at multiple quantization levels. Real runs, not estimates.
Quantizations measured: Q4, Q5, Q6, Q4_K_M, Q8
5
Benchmark rows
2
Chip tiers covered
92.1
Fastest avg tok/s (M4 Max (40-core GPU, 64 GB))
16.12 GB
Minimum RAM observed
Benchmark results for Qwen 3 30B A3B
Rows sorted by avg tok/s descending. Click source badge to see original measurement page.
Chips with published results for Qwen 3 30B A3B
Data
benchmarks.json — full dataset · models.json — model summaries · benchmarks.csv — CSV export