Latency
7 posts tagged #latency
7 posts on Latency, 4 of them in the AI in Production pillar, with 2 in Dev Tools & AI Workflow — most read: “5 LLM APIs Tested for Latency: Real Data [2026]” and “Streaming TTFT Benchmark: Argon vs Opus 5.5 vs GLM-5.2”.
AI and Machine Learning Streaming TTFT Benchmark: Argon vs Opus 5.5 vs GLM-5.2
I ran all three new frontier models through the same streaming harness. Gemini 4 Argon hit 290ms TTFT, Opus 5.5 lagged, and open-weight GLM-5.2 surprised. Real p50/p95/p99 numbers inside.
AI and Machine Learning Mercury 2.5 770 tok/s Benchmark: The Production Playbook [2026]
Mercury 2.5 is clocking ~780 tok/s on Artificial Analysis. At that speed, decode stops being your bottleneck. Here’s what actually changes in production: batching, streaming UX, context packing, cost controls, and evals that don’t lie.
Developer Tools How to Build a Gemini 3.8 Live Voice Agent [2026 Tutorial]
A practical Gemini 3.8 Live real-time voice agent tutorial: full-duplex streaming, barge-in interruptions, async tool calls, ephemeral tokens, and a latency budget you can actually hit.
Technology Xbox Cloud Gaming Pay‑As‑You‑Go Latency: Fix Input Lag Fast [2026]
If Xbox Cloud Gaming goes pay‑as‑you‑go, latency becomes a tax. Here’s the measurement-first workflow and home network settings that actually cut input lag.
AI and Machine Learning LLM Latency Benchmark Methodology: Streaming UX Metrics [2026]
A UX-first LLM latency benchmark methodology for streaming chat and agent apps: measure chunk cadence, jitter, tool-call stall time, and end-to-end time-to-usable—not just TTFT.
Developer Tools Rust Allocator: jemalloc vs mimalloc vs tcmalloc for P99 [2026]
Allocator switching can cut P99 latency in Rust services. It can also do absolutely nothing. Here’s how to benchmark it like an adult and tune jemalloc without cargo-culting.
Technology 5 LLM APIs Tested for Latency: Real Data [2026]
I benchmarked Claude Haiku 4.5, Claude Sonnet 4, GPT-4.1, GPT-4.1 Mini, and Gemini 2.5 Flash for TTFT, throughput, and end-to-end latency — with a cost-latency decision matrix for production builders.
Keep exploring
Close to this topic, not on this page.
