Kimi Dev 72b
Kimi Dev 72b is an open-weights language model from Moonshot AI, released June 16, 2025. It has 72B parameters (dense).
1. Kimi-Dev-72B achieves 60.4% performance on SWE-bench Verified. It surpasses the runner-up, setting a new state-of-the-art result among open-source models. 2. Kimi-Dev-72B is optimized via large-scale reinforcement learning.
Check it against your own PC →
Can you run Kimi Dev 72b locally?
The smallest common GPU it runs on is 24 GB of VRAM (with 32 GB of RAM): IQ2_XXS, split GPU / CPU, roughly 22 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 5.2 GB | 18.3 GB | ~2 |
| 8 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 7.2 GB | 16.3 GB | ~2 |
| 12 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 11.2 GB | 12.3 GB | ~2 |
| 16 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 15.2 GB | 8.3 GB | ~3 |
| 24 GB VRAM | Runs, slowly | IQ2_XXS (heavy loss) | 23.2 GB | 0.3 GB | ~22 |
| 32 GB VRAM | Runs on GPU | IQ2_M (heavy loss) | 29.3 GB | – | ~42 |
Benchmark results
Epoch AI has not published results for Kimi Dev 72b yet. New models are usually evaluated within days to weeks.
Links
More from Moonshot AI
Kimi K3.1 Pro · Kimi K3 · Kimi K2.7 Code · Kimi K2.6 · Kimi K2.5 · Kimi K2 Thinking · Kimi Linear · Kimi K2 (Jul 2025)