Kimi-K3
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning.
Params
2,779.9 B
Context
—
Downloads 30d
2.1 M
Likes
11,433
Download history
daily snapshots · 48 days
▲ 213 K in the last 30 days (9.1%)
2.9 M2.1 M
Aug 22Sep 1Sep 11Sep 20
2.9 M968 K
Aug 4Aug 20Sep 5Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | u8 | 1,560.9 GB | 2,134.5 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- KimiK3ForConditionalGeneration
- Parameters
- 2,779.9 B
- Tensor type
- U8
- Licence
- other
- First seen on the Hub
- 2026-06-13
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-04
Compare with any image-text-to-text model