cjpais / cjpais/LocalScore

Score looks wrong for Apple M1 Mac studio

Open
#30 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
132
Forks
17
PR merge metrics
No merged PRs in 30d

Description

My M1 Max Mac studio with 64gb unified memory had somehow a worse score than my RTX 3070 system with 16gb ram (score) . The result looks off compared to the system average results https://www.localscore.ai/accelerator/688. For reference, GPT-OSS 20B performs at near chatgpt ~100 token/sec on this machine, but the results show average of under 20 tokens/sec.

Probably missing GPU offload capability ?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Compare the linked LocalScore result pages 2554 and 2553 with the accelerator average at 688, then investigate how the benchmark handles GPU offload on Apple M1 systems. Done means the M1 Max result reflects its observed performance and the scoring discrepancy is explained or corrected.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.