Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
Today we release Needle 2: an open 45M-parameter model for tool calling, device use and structured extraction. The whole model is a single 14MB binary that runs a full session in 28MB of RAM. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, between 400–1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300–700 on sub-$200 phones such as the Samsung A-Series.
- ▪Today we release Needle 2: an open 45M-parameter model for tool calling, device use and structured extraction.
- ▪The whole model is a single 14MB binary that runs a full session in 28MB of RAM.
- ▪Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, between 400–1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300–700 on sub-$200 phones such as the Samsung A-Series.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,318 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Cactus Compute |
| Canonical URL | https://cactuscompute.com/needle |
| Publication time | Mon, 10 Aug 2026 17:22:07 +0000 |
| Retrieval time | 2026-08-10T17:40:44.963Z |
| Last seen | 2026-08-10T17:40:44.963Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 0nW7ch-PmZQN · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Today we release Needle 2: an open 45M-parameter model for tool calling, device use and structured extraction. The whole model is a single 14MB binary that runs a full session in 28MB of RAM. It is built on our Simple Attention Network findings, compressed to CQ2-bit with Cactus Quants, and baked into its own engine.On the tool call and mobile device use benchmarks, Needle 2 trades wins with other small models like FunctionGemma 270M, LFM2.5 230M and Apple FM, at 5× to 70× smaller, and 2 bits against their f16. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, between 400–1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300–700 on sub-$200 phones such as the Samsung A-Series.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Cactus Compute.
Discussion
0 commentsMore from Cactus Compute
