Kimi K3 Open Source: 2.8T Parameters and 1M Token Context
usamawahabkhan · x · 2026-07-29
Moonshot AI's Kimi K3 model is now available on vLLM. The model features 2.8 trillion parameters using a Mixture-of-Experts architecture, with 16 experts active per inference. K3 supports a 1M-token context window and native multimodal understanding. Additionally, it introduces Kimi Delta Attention, a hybrid of linear and full attention that significantly reduces the computing cost for million-token contexts.
Related event: Kimi K3 shifts attention from scale to architecture(25 posts)→
More from Models
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- Fully local voice assistant on an RTX 3060 replicates the GPT Live demo in 6.5 minutes — liampetti · 2026-09-11
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11