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.
More from Models
- Users Petition OpenAI for $400-$600 Heavy Builder Tier as $200 Plan Runs Dry in 48 Hours — dragonwarrior_1 · 2026-09-10
- Leak: 'SpaceXAI' working to bring Grok Bots into XChat for in-conversation tagging — nima_owji · 2026-09-10
- Chinese model's 74.2 score under fire: best of 8 eval variants, maxed thinking budget, ~2.5x cost — teortaxesTex · 2026-09-10
- Unitree fully open-sources UnifoLM-WLA-1.0, a 6B humanoid robot foundation model — teortaxesTex · 2026-09-10
- DeepSeek's new release shows ChatGPT fingerprints, token efficiency set to jump — teortaxesTex · 2026-09-10
- Analyst: DeepSeek's latest change is a big win for token efficiency, moving toward OpenAI's regime — teortaxesTex · 2026-09-10