Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is an open-weights language model from Moonshot AI, released July 11, 2025. Its makers disclosed about 1T parameters. On the Epoch Capabilities Index it scores 141.2, rank 116 of 256 rated models.
Kimi K2 is our latest Mixture-of-Experts model with 32 billion activated parameters and 1 trillion total parameters. It achieves state-of-the-art performance in frontier knowledge, math, and coding among non-thinking models.
Check it against your own PC →
Can you run Kimi K2 (Jul 2025) locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. 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 | Size unknown | – | – | – | – |
| 8 GB VRAM | Size unknown | – | – | – | – |
| 12 GB VRAM | Size unknown | – | – | – | – |
| 16 GB VRAM | Size unknown | – | – | – | – |
| 24 GB VRAM | Size unknown | – | – | – | – |
| 32 GB VRAM | Size unknown | – | – | – | – |
Parameter count unknown. The weights may not be on Hugging Face yet.
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Coding | 33.9 | Aider polyglot, GSO-Bench, Terminal Bench |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| Aider Polyglot | 59.1% |
| Terminal-Bench | 27.8% |
| SimpleBench | 11.6% |
| GSO-Bench | 4.9% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Gemini 3.1 Flash-Lite · Gemini 2.5 Pro (Jun 2025) · Claude Opus 4.1 · DeepSeek-V3.2-Exp · Grok 4 Fast · Gemma 4 31B IT · Qwen 3.6 35B-A3B · Qwen3.5-35B-A3B
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-VL