Kimi K3 with 2.8T parameters and 1M context now supported on vLLM
ricklamers · x · 2026-07-27
vLLM announces Day-0 support for Moonshot AI's Kimi K3, one of the most powerful open-weight models. K3 features 2.8T parameters (MoE, 16/896 experts active), 1M context window, native multimodal understanding including vision, and Kimi Delta Attention (hybrid linear and full attention) for affordable long context. Thanks to partners Moonshot, inferact, NVIDIA, AMD.
More from Models
- Kimi K3 launches on SGLang with 423 tok/s and 11 cloud partners — ying11231 · 2026-07-28
- Anthropic’s Opus 5 tops a ReactBench claim while costing more than 2× less — aidenybai · 2026-07-28
- Viral post claims OpenAI will preview GPT-6 in Washington with science and cyber gains — iamaliveix · 2026-07-27
- Moonshot’s Kimi K3 hits No. 1 on Hugging Face trends within 30 minutes — huggingface · 2026-07-27
- Ollama Adds Kimi K3: 1M Context Window and Native Vision Support — ollama · 2026-07-27
- Kimi K3 reportedly improves training efficiency by 2.5× — zephyr_z9 · 2026-07-27