RTX 4090 vs MI300X
Signed, community-submitted decode tok/s, prefill, and TTFT for RTX 4090 vs MI300X — every number links to the run it came from.
Verdict
MI300X has no submitted run yet, so there is no head-to-head number to report. We do have 8 models measured for RTX 4090 (peak 195 tok/s decode on gemma3) — the table below is that baseline. Run the llm-speed suite on MI300X and this page fills in the second column automatically.
RTX 4090 benchmarks — no shared model with MI300X yet
| Model | decode tok/s | Workload | Run |
|---|---|---|---|
| gemma3 | 195.0tok/s | chat-short | r_dlanfbgym0h |
| qwen3-coder | 179.9tok/s | concurrent-decode | r_wjq32z47vlp |
| qwen2.5-coder | 161.1tok/s | concurrent-decode | r_mv8n8k9wu1e |
| llama3.1 | 154.4tok/s | chat-short | r_h1ub_1uxzdh |
| gpt-oss | 141.7tok/s | chat-long | r_iu2sfa9ykvw |
| deepseek-r1 | 133.8tok/s | agent-trace | r_fg77v2hhohb |
| glm-4.7-flash | 129.9tok/s | agent-trace | r_o636l3cc-rr |
| qwen3.6 | 44.18tok/s | agent-trace | r_h_659oy695r |
See also: RTX 4090 benchmarks · MI300X benchmarks · All hardware · All models · Methodology