P1-235B-A22B
P1-235B-A22B is an open-weights language model from Shanghai AI Lab, released November 17, 2025. It has 235B parameters (mixture-of-experts, 22B active). The context window is 256K tokens.
Recent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand against nature, not merely fit a rubric.
Check it against your own PC →
Can you run P1-235B-A22B locally?
The smallest common GPU it runs on is 32 GB of VRAM (with 32 GB of RAM): IQ1_M, GPU + experts in RAM, roughly 18 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 | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Runs · GPU + CPU experts | IQ1_M (experimental) | 31.2 GB | 24.0 GB | ~18 |
Ready-made quantizations on Hugging Face: introvoyz041/P1-235B-A22B-mlx-4Bit
Benchmark results
Epoch AI has not published results for P1-235B-A22B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: PRIME-RL/P1-235B-A22B