Liquid AI launches RIPL inference engine, cuts latency 14‑28× vs Qwen3.5

Liquid AI released RIPL, a real-time inference engine for its LFM models; on a B200 GPU LFM2.5‑1.2B on RIPL achieved 14.4‑28.4× lower p95 latency than Qwen3.5‑0.8B running on vLLM.

Benchmarks are the company's own; not independently verified.

Why it matters

Benchmark RIPL's latency gains for LFM models; users will expect sub‑50 ms inference.

For product managers

For your product

What does this mean for your product?

Try it on your product

Read at MarkTechPost

More from this issueAll AI news from 23 Oct →

OpenAI seeks $30B raise at $1.25T valuation, sources sayUnconfirmed

OpenAI Makes Decisions API Widely Available, Challenging TypeSafe’s JevAvailable now

Google launches Agent Compute Engine giving each Gemini agent its own microVMAnnounced

Anthropic releases Claude Duet proactive agent in research previewAnnounced

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an invite See how it works