ProductsMulti-sourceSelected73°

Perplexity releases open source models

Why we picked it

These contributions position Perplexity as a serious open-source player beyond its search interface. Developers can leverage these specialized tools for better performance in multimodal tasks, embeddings, and on-device processing, particularly valuable for privacy-sensitive applications. The releases offer concrete alternatives to proprietary solutions with measurable performance gains.

Perplexity launched pplx-decider-v1-27b, a multimodal decision model scoring 85.

Body

7% across 11 benchmarks.The company also released pplx-embed-v2-context-9b-preview, achieving best results on ConTEB and turbopuffer context-bench.

Lily, a local inference engine for Apple silicon, delivers 1.23x faster prefill and 1.

35x faster decode than MLX-LM on an M5 Max.

Original · Aravind Srinivas

a few open source contributions from perplexity recently: •pplx-decider-v1-27b: SoTA multimodal decision model. 85.7% average across 11 benchmarks, ahead of Jev. •pplx-embed-v2-context-9b-preview: SoTA contextual embeddings, best on ConTEB and turbopuffer context-bench. •Lily: local inference engine for Apple silicon. rust plus custom metal kernels, no pytorch or mlx. 1.23x faster prefill and 1.35x faster decode than MLX-LM on an M5 Max •PII-Tracer: 0.6B on-device PII classifier that decides when a hybrid compute task stays on your Mac. beats OpenAI’s Privacy Filter on all 5 public benchmarks. also released with the PII-TRACE benchmark: 13k conversations in 13 languages •WANDR: benchmark for wide and deep research agents. 500 tasks needing 170k source-backed records •Numbat: agent detection and response for laptops and workstations. 52 rules, single go binary for macOS, linux and windows •Bumblebee: read-only supply chain scanner for dev machines. covers packages, MCP configs, and editor and browser extensions. a lot more open source contributions coming soon!📊 61 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Perplexity, pplx-decider, Lily, multimodal.

Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 3 independent sources have covered this development (including IT之家, Blognone), confirming industry-wide signal strength.