Compare
Compare local AI hardware with workload-aware output.
Operating mode: Balanced. Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
NVIDIA GB200 192GB wins for coding in balanced mode
Based on model fit, speed, and quality across top recommendations.
NVIDIA GB200 192GB
WinnerSDevstral 2 123B Instruct
llama.cppQ4_K_MRuns well
100.5 GB / 192.0 GB
97.4 tok/s256K ctx
SQwen 3.5 122B A10B
llama.cppQ4_K_MRuns well
97.0 GB / 192.0 GB
270.2 tok/s131K ctx
SMistral Small 4 119B
llama.cppQ4_K_MRuns well
98.1 GB / 192.0 GB
292.9 tok/s256K ctx
B100 192GB
SDevstral 2 123B Instruct
llama.cppQ4_K_MRuns well
100.5 GB / 192.0 GB
97.4 tok/s256K ctx
SQwen 3.5 122B A10B
llama.cppQ4_K_MRuns well
97.0 GB / 192.0 GB
270.2 tok/s131K ctx
SMistral Small 4 119B
llama.cppQ4_K_MRuns well
98.1 GB / 192.0 GB
292.9 tok/s256K ctx
Quick comparison
| Metric | NVIDIA GB200 192GB | B100 192GB |
|---|---|---|
| Models that fit | 3 | 3 |
| Avg decode tok/s | 220.2 | 220.2 |
| Best grade score | 96 | 96 |