← All benchmarks

Qwen 2.5 14B — Apple Silicon Benchmarks

Measured inference speed for Qwen 2.5 14B across 1 Apple Silicon chip. Tokens per second at multiple quantization levels. Real runs, not estimates.

Quantizations measured: Q3_K_L

1 Benchmark rows
1 Chip tiers covered
18.6 Fastest avg tok/s (M4 Pro (12-core GPU))
8 GB Minimum RAM observed

Benchmark results for Qwen 2.5 14B

Rows sorted by avg tok/s descending. Click source badge to see original measurement page.

Chip Quant RAM req. Context Avg tok/s Prompt tok/s Runtime Source
M4 Pro (12-core GPU) Q3_K_L 8.0 GB 4k 18.6 tok/s ref

benchmarks.json — full dataset  ·  models.json — model summaries  ·  benchmarks.csv — CSV export

See all models →