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.

Radeon RX 7700S 8GB wins for coding in balanced mode

Based on model fit, speed, and quality across top recommendations.

Winner

SQwen 3.5 4B

llama.cppQ4_K_MRuns well

6.3 GB / 8.0 GB

56.0 tok/s28K ctx

AGemma 4 E2B

llama.cppQ4_K_MRuns well

5.3 GB / 8.0 GB

45.0 tok/s96K ctx

ACodestral Mamba 7B

llama.cppQ4_K_MRuns well

6.5 GB / 8.0 GB

45.8 tok/s67K ctx

SQwen 3.5 4B

llama.cppQ4_K_MRuns well

6.3 GB / 8.0 GB

48.0 tok/s28K ctx

AGemma 4 E2B

llama.cppQ4_K_MRuns well

5.3 GB / 8.0 GB

61.2 tok/s96K ctx

ACodestral Mamba 7B

llama.cppQ4_K_MRuns well

6.5 GB / 8.0 GB

82.0 tok/s67K ctx

Quick comparison