Ollama Adds Kimi K3: 1M Context Window and Native Vision Support
ollama · x · 2026-07-27
Ollama now supports running the Kimi K3 model. Kimi K3 is an open-weight, native multimodal agentic model with 2.81T (3T-class) parameters, touted as Kimi's most capable model to date.
Built on the Kimi Delta Attention (KDA) and Attention Residuals architecture, the model supports a massive 1-million-token context window and native vision capabilities. Currently, running Kimi K3 via Ollama requires a Pro or Max subscription and consumes extra usage credits.
More from Models
- Kimi K3 launches on SGLang with 423 tok/s and 11 cloud partners — ying11231 · 2026-07-28
- Kimi K3 reportedly improves training efficiency by 2.5× — zephyr_z9 · 2026-07-27
- NVIDIA distills Cosmos3 Super image-to-video to 4 steps with a 64B model — multimodalart · 2026-07-27
- Kimi K3 goes live on Modal with custom DFlash speculative decoding for lossless speedup — AAAzzam · 2026-07-27
- Kimi K3 with 2.8T parameters and 1M context now supported on vLLM — ricklamers · 2026-07-27
- Kimi K3 could become a cheap distillation base for personal, local models — victormustar · 2026-07-27