Kimi K3 — local AI model by Moonshot AI
Written by Jakub Rusinowski · Last updated
Moonshot AI's July 2026 flagship and its largest model to date — a 2.8-trillion-parameter Mixture-of-Experts that landed in the July 16–27 window. K3 roughly doubles the expert count of Kimi K2.5 (1T) while keeping active parameters modest (~48B per token), pushing Moonshot's lead on agentic coding, tool use, and long-horizon reasoning further ahead of K2.6. Natively multimodal with a 256K context. At this scale it is a data-center / API model — self-hosting needs well over a terabyte of memory even at Q4, so most users reach it through the Kimi API or the smaller K2.x community builds.
Variants
The smallest Kimi K3 variant needs about 1691 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Kimi K3 2.8T → 2.8T/104B active | ~1691.3 GB | 1,000,000 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Kimi K3 locally
Install Ollama, then pull the tag.
No local Ollama tag. Ollama lists kimi-k3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: Kimi K3 2.8TCan I run Kimi K3 on my GPU?
Kimi K3 — frequently asked questions
How much VRAM does Kimi K3 need?
Kimi K3 needs about 1691 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Kimi K3 2.8T (1691 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Kimi K3 on an RTX 4090 (24 GB)?
Kimi K3's smallest variant needs about 1691 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for Kimi K3?
Q4_K_M is the best balance of quality and VRAM for Kimi K3 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Kimi K3 with Ollama?
Kimi K3 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.