Alleged 14T-parameter "Mythos-class" model leak on Hugging Face debunked as fake
burny_tech · x · 2026-11-02
- A mysterious Hugging Face repo claimed: 14 trillion parameters, 1,224 MoE experts, 7.72 TB of weights across 772 shards, hybrid GDN+MLA architecture, plus configs and training metadata
- Nobody had verified the weights
- Developer nisten inspected and called it fake/garbage: 553B active params, Chinese-style tokenizer, subpar architecture choices, weights seemingly autogenerated from filename hashes
More from Models
- amasad warns subsidized AI subscriptions will get 'rug pulled' as Grok users hit limits faster — amasad · 2026-11-02
- vLLM serves DeepSeek-V4.1-Flash at 954K tokens/s per GPU on one GB300 NVL72 rack — bookwormengr · 2026-11-02
- OpenAI now caps paid ChatGPT accounts per device and payment card — Alone-Dragonfruit602 · 2026-11-02
- Tracker: Chinese open-weight models ~6-8 months behind frontier, gap widening past a year — scaling01 · 2026-11-02
- Google reportedly testing Gemini 4 Carbon checkpoint on Arena disguised as Argon 4 — testingcatalog · 2026-11-02
- 550M-param AlphaFold3 unbeatable on cost/quality, sparking small-vs-big model debate — nlarusstone · 2026-11-02