Benchmarks · community-measured

bonsai-1.7b-2bit on Apple M5 Max

Real measured local-inference performance for bonsai-1.7b-2bit on an Apple M5 Max (36 GB unified memory), from the rapid-mlx community benchmark corpus. Latest submission 2026-08-21, measured on rapid-mlx 0.12.18.

329
tok/s decode
10550
tok/s prefill
204 ms
first token
3.7 GB
peak memory

Aggregated from 9 community runs.

All measurements for this pair

RAMAccelDecodePrefillTTFTPeak memRunsrapid-mlxLatest
36 GB329 tok/s10550 tok/s204 ms3.7 GB90.12.182026-08-21

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 bonsai-1.7b-2bit --tier speed --submit

More

bonsai-1.7b-2bit model page · Small & curated models · Interactive leaderboard · Alias catalog