gpt-oss-120b on GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)

1. Decode: reading 5.1B active parameters at 4.25 bits/weight takes 25.29 ms at 256 GB/s x 42% achieved efficiency.
2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
3. Prefill: 59 TFLOPS (FP16) x 18% assumed model-FLOPs utilisation, divided by 2 x 24.4B parameters per token.
4. Prefill uses 24.4B effective parameters, not the 5.1B active in decode: a batch of hundreds of tokens routes across most of the expert pool.

• MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
• Prefill throughput is highly engine-dependent. Flash attention, batch size and quantized KV all move this number substantially, and for sparse mixture-of-experts models it is the least reliable figure we produce.
• This is a calculated estimate, not a measurement. It assumes a single request, a short prompt, no speculative decoding and a warm model already resident in memory.

Estimator version estimator_v1. Stored with every estimated row so old estimates can be regenerated when the model improves.

• Community-reported benchmark: +2
• 1 measurement: +0
• Single measurement — agreement cannot be assessed: +0
• Incomplete run metadata: +0

Score 2/10. Aggregated with the median, not the mean, so one outlier cannot move the headline figure.