Kimi Dev 72B
72.7B parameters · 128k context · MIT · released 2025-06-16
codingagentic
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
A 72B coding model built on Qwen2.5-72B and tuned for resolving software issues, scoring 60.4% on SWE-bench Verified. The card says it was trained with reinforcement learning to patch real repositories in Docker.
Questions
- What licence is Kimi Dev 72B released under?
- MIT, which allows commercial use.