@agupta: I love that in this arms race for speed there is a seed stage YC company @wafer_ai fighting for the top spot
Summary
A seed-stage YC startup, Wafer AI, is competing in the inference speed race, with Databricks achieving 392 token/s on GLM-5.2, topping Artificial Analysis.
View Cached Full Text
Cached at: 06/25/26, 09:28 PM
I love that in this arms race for speed there is a seed stage YC company @wafer_ai fighting for the top spot
Yuchen Jin (@Yuchenj_UW): You may have heard that GLM-5.2 at 328 token/s is cool,
How about 392?
Databricks is now #1 in inference speed for GLM-5.2 on Artificial Analysis. It’s a great model, and we did a lot of optimizations.
Similar Articles
@mogulinfluence: Read this if you want to know what YC and Sequoia are actually betting on in AI space right now:
This post highlights a resource detailing the current investment focus of Y Combinator and Sequoia Capital within the AI industry.
@gabriel1: inference will be the biggest market in the world, intelligence is in infinite demand etched is bringing the AI Summer
Etched, an AI inference hardware startup, exited stealth after raising $800M and securing over $1B in customer contracts. Their first racks ship this summer, claiming state-of-the-art throughput, latency, and power efficiency.
@mattshumer_: Nvidia has some serious competition coming their way.
Etched emerges from stealth with AI inference hardware, claiming state-of-the-art throughput and efficiency, posing serious competition to Nvidia.
@philipkiely: https://x.com/philipkiely/status/2069212319746506968
Baseten announces the world's fastest API for the GLM-5.2 open model, achieving over 280 tokens per second via NVFP4 quantization, disaggregated inference, and other optimizations.
@MiaAI_lab: Nvidia did it again! @NVIDIAAI's Qwen 3.6 27B NVFP4 is faster than Unsloth's Qwen 3.6 27B NVFP4 by a whopping ~41% on D…
Nvidia's optimized Qwen 3.6 27B NVFP4 model achieves 41% faster single-session inference and 23-25% faster concurrent inference on DGX Spark compared to Unsloth's version.