Story
Smaller, faster, safer: running Kimi and GLM at scale
1 report
1 website
1 discussion
Latest report
Overview
Workers AI runs inference for Moonshot's Kimi K-series and Z.ai's GLM models on GPUs in Cloudflare data centers. These models are large, long-context, and mixture-of-experts types, presenting challenges in efficient serving due to memory constraints.
Summary from blog.cloudflare.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
blog.cloudflare.com
Smaller, faster, safer: running Kimi and GLM at scale
Read report →
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · blog.cloudflare.com
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-08-04.
- Praise: Nice to see a provider being transparent about KV cache quantisation — transparency is key in a field where subtle changes can make or break performance.
- Praise: The claim that FP8 KV quantisation can deliver meaningful latency and capacity gains with negligible accuracy loss is a promising development in model efficiency.
- Concern: The benchmarks used to assert that FP8 KV quantisation is indistinguishable are lacking, especially since they omit critical coding benchmarks that could reveal serious issues.
- Concern: Serving quantized models without clearly stating it feels deceptive, especially when the impact on coding agents could be significantly negative.