Kimi K2.7 Code
1026.9B total, 33.3B active · 256k context · Modified MIT License · released 2026-06-11
codingagenticvisionreasoningchat
What to run it on in Germany
Fully in memory at 128k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
1T-parameter MoE (32B active) with native INT4 quantization; recommended engines are vLLM, SGLang and KTransformers, with transformers >=4.57.1,<5.0.0. Thinking mode is forced (no instant mode), and the custom Modified MIT licence terms are not spelled out in the card, so check the LICENSE file.
Questions
- What licence is Kimi K2.7 Code released under?
- Modified MIT License.