Coding with AI / RX 7900 XT
RX 7900 XT
Memory: 20 GB.
Memory bandwidth: 800 GB/s.
Generation speed is bound by the chip's bandwidth; memory decides which models fit.
smart and fastgpt-oss-20b60.7% on SWE-bench Verifiedfrozen102 tok/s · measured How to run
gpt-oss-20b smart
-
Score: 60.7% (SWE-bench Verified),
source
-
Speed: 101.92 tok/s (measured, source)
- Conditions: engine llama.cpp, quant MXFP4, context 128
- Min memory: 12 GB
- Command:
llama-server -m gpt-oss-20b-MXFP4.gguf
Every number above is either a measurement with a source or a labeled estimate with a method.
Unlabeled estimates do not exist on this site.
Ceiling timeline
The strongest model fitting RX 7900 XT (20 GB) at its release date, by SWE-bench Verified.
- 2025-08-05 gpt-oss-20b 60.7%
- 2025-08-05 gpt-oss-120b 62.4%
- 2025-12-09 Devstral Small 2 68%