Also, since DeepSeek 4.1 Flash is already quite quantized, the same OpenRouter benchmark harness puts us at #9, but the first 10 places (out of about 30) are within less than 1% of each other - so that is much harder to set.
But here, again, we run on B200, the official weights with specific configurations that we have on vllm.
But here, again, we run on B200, the official weights with specific configurations that we have on vllm.