Benchmarks · community-measured

qwen2.5-14b-4bit on Apple M5 Max

Real measured local-inference performance for qwen2.5-14b-4bit on an Apple M5 Max (36 GB unified memory), from the rapid-mlx community benchmark corpus. Latest submission 2026-08-12, measured on rapid-mlx 0.12.10.

43.5
tok/s decode
1176
tok/s prefill
1.8 s
first token
8.7 GB
peak memory

Aggregated from 2 community runs.

All measurements for this pair

RAMAccelDecodePrefillTTFTPeak memRunsrapid-mlxLatest
36 GB43.5 tok/s1176 tok/s1.8 s8.7 GB20.12.102026-08-12

Standardized single-request benchmark: 5 measured rounds after 1 discarded warmup, greedy sampling, prefix cache disabled. Raw corpus: /api/benchmarks.

Reproduce this number

Install rapid-mlx, run the same suite on your Mac, and submit the result — it lands on the community leaderboard and updates this page.

$ curl -fsSL https://rapidmlx.com/install.sh | bash
$ rapid-mlx bench qwen2.5-14b-4bit --tier speed --submit

More

Qwen family · Interactive leaderboard · Alias catalog