Comment by coder543
2 months ago
The Spark has more compute, so it should be faster for prefill (prompt processing).
The M4 Max has double the memory bandwidth, so it should be faster for decode (token generation).
2 months ago
The Spark has more compute, so it should be faster for prefill (prompt processing).
The M4 Max has double the memory bandwidth, so it should be faster for decode (token generation).
No comments yet
Contribute on Hacker News ↗