Best for
Primary discovery source is Hacker News. / A public GitHub repo is available for direct technical review.
Needle: We Distilled Gemini Tool Calling into a 26M Model
- Hacker News
Product Summary
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on b...
Why it matters
Primary discovery source is Hacker News.
Key Features
- Primary public product URL is https://github.com/cactus-compute/needle.
- Description: Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the litt....
- GitHub repository is linked as cactus-compute/needle.
- Listed on Hacker News as "Needle: We Distilled Gemini Tool Calling into a 26M Model".
- Source description: Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the litt....
Use Cases
- Primary discovery source is Hacker News.
- A public GitHub repo is available for direct technical review.
- Hacker News mention is recent (2026-05-12).
- Primary public product URL is https://github.com/cactus-compute/needle.
- Description: Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the litt....
Why Now
Needle: We Distilled Gemini Tool Calling into a 26M Model is appearing on fresh discovery surfaces, so it is worth reviewing while momentum is still forming. Confidence is currently medium (49/100), so treat this as an early signal rather than a settled trend.
Intelligence Breakdown
Facts
- Listed on Hacker News as "Needle: We Distilled Gemini Tool Calling into a 26M Model".
- Source description: Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the litt....
- Source publish date is 2026-05-12.
- Description: Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the litt....
- GitHub repository is linked as cactus-compute/needle.
- Primary public product URL is https://github.com/cactus-compute/needle.
Signals
- Hacker News mention is recent (2026-05-12).
- A public GitHub repo is available for direct technical review.
- Primary discovery source is Hacker News.
Inference
- Public code access can lower evaluation friction for developer audiences.
Unknowns
- Documentation is not explicitly linked in the current allowed evidence set.
- No tagline is stored on the current product record.
- Pricing details are not explicitly linked in the current allowed evidence set.
- Recent changelog or release history is not explicitly linked in the current allowed evidence set.
- Release cadence cannot be confirmed unless a changelog or release link is explicitly provided.
Evidence Snapshots
Needle: We Distilled Gemini Tool Calling into a 26M Model
Listed on Hacker News as "Needle: We Distilled Gemini Tool Calling into a 26M Model".
Needle: We Distilled Gemini Tool Calling into a 26M Model GitHub repository
GitHub repository is linked as cactus-compute/needle.
Needle: We Distilled Gemini Tool Calling into a 26M Model official profile
Primary public product URL is https://github.com/cactus-compute/needle.