MLX Tested: M2 Max Hits 514 tok/s On-Device
MaziyarPanahi · x · 2026-07-04
To verify the "729 tok/s" claim, the author benchmarked four v2 MLX builds under identical conditions: same clinical corpus, single stream, batch 1, and decoding overhead included. Results show 8-bit outperforms fp16 on both models, hence its use in the demo. A standard M2 Max laptop achieved 514 tok/s entirely on-device.
More from Infra
- Anthropic S-1 reveals 48 cents of compute cost per dollar of Q2 revenue — nmasc_ · 2026-10-26
- Persistent AI joins UR network to route private AI inference with encrypted, IP-hidden traffic — 0xSammy · 2026-10-26
- Anthropic's disclosed compute commitments: $114.5B Google, $161.2B Broadcom top the list — BenBajarin · 2026-10-26
- SpaceX strikes $40B deal with Apollo Global to lease AI chips and data center hardware — Polymarket · 2026-10-26
- SpaceX AI revenue up 830%, Claude designs 318K antivenom proteins in 64 hours — PeterDiamandis · 2026-10-26
- Meta plans up to $95 billion stock sale to fund AI buildout — The Decoder · 2026-10-26