💻 Technology 9h ago

DeepSeek V4 Pro has 1.6T total parameters, its largest model by that metric, and V4 Flash has 284B parameters; both models have a context window of 1M tokens (South China Morning Post)

Techmeme
View Channel →
Source ↗ 👁 0 💬 0
South China Morning Post:
DeepSeek V4 Pro has 1.6T total parameters, its largest model by that metric, and V4 Flash has 284B parameters; both models have a context window of 1M tokens  —  The company says its cost-efficient new V4 model is competitive with top closed-source models from OpenAI and Google DeepMind

Comments (0)

Sign in to join the discussion

More Like This

Apple TV’s twisted new comedy hailed as ‘unlike anything else on TV’
9to5Mac · 32m ago
I gave Claude Code persistent memory and now it's unstoppable
XDA · 38m ago
📰
Sabotaging projects by overthinking, scope creep, and structural diffing
Hacker News · 39m ago
Cool phones are not dead, and this liquid-cooled gaming phone proves it
Digital Trends · 40m ago
Jio Platform Q4: Net Profit Increases 13% to ₹7,935 Cr
Inc42 Media · 45m ago
Verda raises $117M, Aleph Alpha to be acquired, and solving the quantum bottleneck
Tech.eu · 46m ago