MacBook Pro M3 Max 64 GB Apple Silicon Benchmarks

Name: MacBook Pro M3 Max 64 GB Apple Silicon Benchmarks
Creator: COEY
Published: 2026-09-03

MacBook Pro, Apple M3 Max, 64 GB unified memory. Timed 2026-08-27 to 2026-09-03.

MacBook Pro M3 Max64 GB unified memory2023

Vision

Wall-clock times for each model on this configuration, still then video chunk.

Each cell is still then video chunk.

Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
Engine: mlx, mlx-vlm 0.6.10
Sidecar: mlx_vlm.server on 127.0.0.1:8788
Batching: Continuous batching on
APC: Off
Response format: json_object
Max tokens: 4000
Warmup: 1 discarded, then 3 stills and 2 chunks
Speculative decoding: off
Default model: mlx-community/gemma-4-e4b-it-4bit
Models locked: Yes
Chunk note: The timed chunk used six frames and the same JSON schema as ingest. Ingest also adds a longer set of rules about merging shots and naming people, which the timed prompt leaves out.

Wall-clock times for each model on this configuration, one line then six lines.

Wall clock on each machine, one line then six lines
Model	MacBook Pro M3 Max 64 GB
1.7B	8.57s / 14.86s

Each cell is one line then six lines.

Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
Engine: mlx
Default model: mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit
Models locked: Yes
Path: Timed through the synthesize_speech tool, so the figure includes the queue and saving the file to the library.
Tier: 1.7B, set once for the whole Mac. It peaks at 11.0 GB of memory, against 2.4 GB for 0.6B.
Voice: Already made and saved. Making a voice is a separate one-time step and is not counted here.

Wall-clock times for each model on this configuration, one clip.

Wall clock on each machine, one clip
Model	MacBook Pro M3 Max 64 GB
LTX 2.5	7m 35s

Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
Engine: mlx
Default model: mlx-community/ltx-2.5-mlx-q8
Models locked: Yes
Path: Timed through the generate_video tool, so the figure includes the queue, the final encode and saving the clip to the library.
Shape: 704 x 1280, 121 frames, 24 fps. All twenty clips were checked afterwards for size and frame count, and all matched.
What was timed: The time between one clip finishing and the next. The queue accepts three jobs at once but renders one at a time, so a job's own elapsed time includes its wait and can roughly double under load.
Cold against warm: The same at this size. At 121 frames the weights are freed after every render and loaded again for the next clip.

Wall-clock times for each model on this configuration, one music bed.

Wall clock on each machine, one music bed
Model	MacBook Pro M3 Max 64 GB
Medium	8.14s

Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
Engine: mlx
Default model: stabilityai/stable-audio-3-optimized
Models locked: Yes
Path: Timed through the generate_music tool, so the figure includes the queue and saving the wav to the library.