Expired50% confidenceFactExact time
A project called Needle (6.7k stars) compresses a model down to just 14MB, enabling it to run directly on a smartwatch.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/22/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/5/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedA tester ran a 20.7B dense model on a dual-4090 (48 GB VRAM) workstation and achieved 27.6 tokens per second, only slightly faster than Dwarf Star, but with over 10 times fewer parameters.65% similarUnverifiedUsing multi-stage builds, the production image of an Astro project can be compressed to the 10–30 MB level, containing neither the Node.js runtime nor the source code.63% similarPartially VerifiedRunning Muse Glimmer at full precision requires 55 GB of VRAM, which is compressed to under 20 GB via 4-bit quantization, allowing it to run on consumer-grade GPUs with 24 GB of VRAM.61% similarVerifiedModels with 32B parameters can typically be compressed to approximately 16–20 GB of VRAM usage after quantization, and can be run on a single NVIDIA RTX 4090 (24 GB VRAM).60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/786769API
curl https://kongchang.com/api/v1/knowledge/claims/786769MCP
get_claim(id=786769)