Compare
Compare local AI hardware with workload-aware output.
RTX 4090 24GB wins for coding in balanced mode
Based on model fit, speed, and quality across top recommendations.
MacBook Pro M1 Pro 32GB
SQwen 3.6 27B
llama.cppq4-k-mTight fit
21.8 GB / 23.0 GB
6.5 tok/s36K ctx
SDevstral Small 2 24B Instruct
llama.cppq4-k-mTight fit
21.4 GB / 23.0 GB
9.5 tok/s27K ctx
AMistral Small 3.1 24B
llama.cppq4-k-mTight fit
21.4 GB / 23.0 GB
9.5 tok/s27K ctx
Quick comparison
| Metric | MacBook Pro M1 Pro 32GB | RTX 4090 24GB |
|---|---|---|
| Models that fit | 3 | 3 |
| Avg decode tok/s | 8.5 | 37.9 |
| Best grade score | 88 | 93 |