Kimi K2.6 on NVIDIA DGX Spark 128 GB

1. Decode: reading 32.0B active parameters at 4.85 bits/weight takes 106.05 ms at 273 GB/s x 67% achieved efficiency.
2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
3. Prefill: 125 TFLOPS (FP16) x 2 for native FP8 tensor cores x 0.85 calibrated against measured prefill on this platform x 18% assumed model-FLOPs utilisation, divided by 2 x 181.3B parameters per token.
4. Prefill uses 181.3B effective parameters, not the 32B 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.