speed-bench: add Apple M5 Max results#584
Open
altdotboy wants to merge 1 commit into
Open
Conversation
Canonical ds4-bench sweep (2048..65536 ctx, step 2048, 128 gen tokens) on Apple M5 Max, 128 GiB, Metal backend, DeepSeek-V4-Flash IQ2XXS. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
thomasjohnflaherty
added a commit
to thomasjohnflaherty/ds4
that referenced
this pull request
Jul 22, 2026
…nt vs antirez#584 Renames the M5 Max CSV/SVG to encode the Q2+Q4 quant mix so this run can coexist with the pure-IQ2XXS M5 Max results in antirez#584 rather than colliding on the shared m5_max.* filename. Content unchanged; SVG name follows the plot_speed.py _ts.svg convention derived from the CSV basename.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a
ds4-benchsweep for the Apple M5 Max (128 GiB), which was not yet inspeed-bench/.Run with the canonical command from
speed-bench/README.md:speed-bench/m5_max.csv(full 32-frontier sweep) andspeed-bench/m5_max_ts.svg(plotted viaplot_speed.py).Representative points:
Decode stays nearly flat past 32k context.
🤖 Generated with Claude Code