AI
Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM
MarkTechPostFriday, August 14, 2026 at 5:45 AM
RedScroll Brief
Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB binary that runs a session in about 28MB of RAM.
RedScroll Signal
- Impact
- High
- Category
- Ai
- Market relevance
- Moderate
- Why it matters
- AI developments move capital, regulation, and competitive advantage across the tech stack. Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB binary that runs a session in about 28MB of RAM. Secondary effects may show up in markets and supply chains linked to Meet Needle and An Open.
Desk copy
RedScroll Briefing
Extractive editorial brief — not a reprint of the original
What happened
Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB binary that runs a session in about 28MB of RAM.
Why it matters
AI developments move capital, regulation, and competitive advantage across the tech stack.
Background
MarkTechPost reported on this under ai. RedScroll surfaces the signal with an extractive brief — not a reprint of the original article. Read the source for full reporting.
Timeline
MarkTechPost published: Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM
Story is in today’s RedScroll edition. Follow the original source for updates.
Economic impact
Secondary effects may show up in markets and supply chains linked to Meet Needle and An Open.
Related stories
- Google AI Releases TimesFM-3: A 330M Parameter Zero-Shot Foundation Model For Multivariate Time Series Forecasting
MarkTechPostAI
- Pacing model development in an era of cyber-critical capabilities
OpenAI NewsAI
- Universitas Gadjah Mada, Indosat and NVIDIA Open Indonesia’s First University AI Center to Develop Local AI Talent
NVIDIA AI BlogAI
- The Open ASR Leaderboard Adds Its First Global South Language
Hugging Face BlogAI
- Jensen Huang says Nvidia achieved AGI, again — not that it matters
The Verge AIAI
- Google AI Introduces EnvHarness: A Programmable Layer That Turns Static Agent Environments Into Adaptive Training Worlds
MarkTechPostAI
Source
MarkTechPost
Original reporting by MarkTechPost. RedScroll provides an extractive briefing only.