Unverified50% confidenceFactExact time
A project titled "A Working Nintendo in ~1GB of Qwen Weights" appeared on Hacker News, claiming to have implemented a working Nintendo emulator with about 1GB of Qwen model weights.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/30/2026
First Seen
Valid until: 11/13/2026
Sources
Related Entities
Related Claims
UnverifiedThe weights of the small Qwen3-0.6B model are only about 1-2GB.67% similarUnverifiedThe Qwen model used in the video test is the 9-billion-parameter version, with a download size of approximately 7.5 GB and a maximum context window of approximately 260,000 tokens.65% similarUnverifiedQwen2 7B模型（70亿参数）运行约需6GB显存64% similarUnverifiedThe developer uses the Qwen3.6-35B-A3B model: it has 35B weights in total, uses only 3B weights when processing each word, has a computational cost comparable to ordinary 4B and 8B models, and runs on their own gateway (vLLM).63% similarUnverifiedQwen has open-sourced multiple model sizes from 0.5B to 72B, covering the full range from phones and laptops to servers, and the community has derived a large number of fine-tuned versions; small models can run offline on ordinary thin-and-light laptops after quantization.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1117246API
curl https://kongchang.com/api/v1/knowledge/claims/1117246MCP
get_claim(id=1117246)