DeepSeek V4.1 Flash reportedly a ~718B sparse model at ~500GB on disk
zainhas · x · 2026-09-10
teortaxesTex tempers excitement over the rumored DeepSeek V4.1 Flash with a spec breakdown: despite the "Flash" branding it's reportedly a 718B-parameter sparse model, similar in size to GLM 5.3 — a 552B mostly-FP4 backbone (307GB) plus 196B FP8 E4M3 Engrams, 500GB on disk, much larger than V4 Flash or GLM 5.3 Flash. Unofficial numbers, but the most concrete technical detail circulating on the leak.
Related event: Leak: DeepSeek V4.1 Flash Is Actually a 718B Sparse Model(2 posts)→
More from Models
- FrontierML benchmark shows open models still far behind closed ones on end-to-end ML work — scaling01 · 2026-10-27
- Mirendil debuts Fern, its first from-scratch model with up to 10M-token context — shayan_ · 2026-10-27
- Week 3 of "Fable 5.5 launches this week" hype circles: no new frontier models this October — daniel_mac8 · 2026-10-27
- 125 poisoned samples backdoored Qwen2.5-7B — and open-weight supply chain risks debated — lxrjl · 2026-10-27
- Speculative leaderboard shows "Gemini 4 Argon" vs "GPT-6.1 Sol"; observer calls MiniMax parity suspicious — teortaxesTex · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27