MLX vs GGUF on Apple Silicon: Benchmarking the Same Local Model Two Ways

说明与用途

MLX 与 GGUF 在构建时间和应用可用性上相当，但 MLX 的方差更低且从未超过 60 分钟限制。GGUF 在计算密集型任务上略快，但更易出现峰值。

问题

Choosing between GGUF and MLX model formats for local coding agents on Apple Silicon, balancing speed, consistency, and quality.

结果

MLX ties GGUF on overall build time and app‑work‑ability, with lower run‑to‑run variance and no 60‑minute caps. GGUF is marginally faster on compute‑heavy tasks but shows higher peak times and occasional caps due to harness bugs.

工作流

• 1. Prepare identical model weights in GGUF and MLX formats.
• 2. Set up a three‑node Apple Silicon fleet with LM Studio serving the model.
• 3. Run swarm‑gym in benchmark mode with the medium tier (5 runs × 3 archetypes).
• 4. Collect structured event logs, per‑task metrics, and golden‑value checks.
• 5. Analyze build times, variance, and app‑work‑ability metrics.
• 6. Identify and fix harness bugs (e.g., integrate‑verify step cap).

证据

MLX had lower run‑to‑run variance (stdev 580s vs 751s), a lower p90 (3050s vs 3601s), and never hit the 60‑minute per‑run cap.

来源

Both builds achieved ~87% app‑works (13/15) when judged by running, despite raw checks favoring MLX.

来源