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.
RX 7700 XT 12GB
SQwen 3.5 9B
llama.cppq4-k-mRuns well
9.8 GB / 12.0 GB
50.8 tok/s32K ctx
ACodeGeeX 4 9B
llama.cppq4-k-mRuns well
8.2 GB / 12.0 GB
51.6 tok/s116K ctx
AGemma 4 E4B
llama.cppq4-k-mRuns well
8.3 GB / 12.0 GB
43.3 tok/s63K ctx
Quick comparison
| Metric | RX 7700 XT 12GB | RTX 4090 24GB |
|---|---|---|
| Models that fit | 3 | 3 |
| Avg decode tok/s | 48.6 | 37.9 |
| Best grade score | 97 | 93 |