Benchmarks · community-measured
lfm2.5-1b-4bit on Apple M1 Max
Real measured local-inference performance for
lfm2.5-1b-4bit on an Apple M1 Max (32 GB unified memory),
from the rapid-mlx community benchmark corpus. Headline submission
2026-08-26, measured on rapid-mlx 0.12.5.
219
tok/s decode
1573
tok/s prefill
1.3 s
first token
1.4 GB
peak memory
A single community run so far — treat it as one data point, not a distribution. Reproduce it below and submit yours to firm it up.
All measurements for this pair
| RAM | Accel | Decode | Prefill | TTFT | Peak mem | Runs | rapid-mlx | Latest |
|---|---|---|---|---|---|---|---|---|
| 32 GB | — | 219 tok/s | 1573 tok/s | 1.3 s | 1.4 GB | 1 | 0.12.5 | 2026-08-26 |
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 lfm2.5-1b-4bit --tier speed --submit
More
lfm2.5-1b-4bit model page · Interactive leaderboard · Alias catalog