Glows.ai

An hourly GPU rate is only half of your inference cost. The other half is how many tokens you get out of each hour. We ran four Qwen3.5 models on the same 48GB L40S, with the same settings: - 35B-A3B (MoE): 122 tok/s - 4B: 102 tok/s - 9B: 61 tok/s - 27B: 21 tok/s Same card, same hour. The fastest model put out about 6× as many tokens as the slowest, so each of its tokens cost about a sixth as much. The fastest one was not the smallest. The 35B-A3B is a Mixture-of-Experts model, so only a small slice of its weights runs for each token. It outpaced the 4B dense model and ran 5.8× faster than the 27B dense one. Parameter count alone did not predict speed. Two caveats. Each number is the best of three runs per model, and the run did not record concurrency. Batching and concurrent requests change throughput per GPU, and the gaps can shift. And speed is not quality: the bigger dense models produced better output than the smaller ones, and the MoE produced the best of all four. Our take: before you compare hourly rates, measure tok/s for your model on the card you plan to use. The rate divided by the throughput is the number that ends up on the bill. When you size an inference deployment, what do you check first: the hourly rate or the tok/s?

AMD Data Center revenue: record $8.5B in Q3, up 97% y/y. Lisa Su on the call: "It is true that demand is higher than supply." When the chipmaker is short, the line forms downstream. Access is the spec. "What do you need to run in Q1?" Get a quote at glows.ai

New to Glows.ai? We turned the whole platform into 9 short videos. From launching your first GPU instance, to snapshots and persistent storage, to sharing a workspace with your team and calling everything from the SDK. About 47 minutes in total. Start at 01, or skip straight to the one you need.

Idle GPUs are empty seats on a plane. Someone pays for them anyway. Own the card, and that someone is you. Rent on demand, and you only pay for your trip. AMA tonight, 8pm Taipei (UTC+8). Link below. "How do we stop paying for idle?" Ask us at glows.ai

Clover-35B: open-weight diffusion LM (35B total, ~3B active), Apache 2.0. Vendor figure: 680 tok/s on one GB300, BF16, batch 1, internal agent workloads. BF16 weights are ~69 GB, so start with one 80 GB card.