Solar Open2 250B
Solar Open2 250B is an open-weights language model from Upstage, released June 28, 2026. It has 250B parameters (mixture-of-experts, 15B active). The context window is 1M tokens.
Solar Open2 250B is an open-source Mixture-of-Experts (MoE) model developed by Upstage. It features 250.3B total parameters with 14.7B active parameters per token. The model is trained on approximately 11 trillion tokens using NVIDIA B200, H200 GPUs.
Check it against your own PC →
Can you run Solar Open2 250B 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 | 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 | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: prometheusAIR/Solar-Open2-250B-GGUF · llamaraspberryrabbit/Solar-Open2-250B-GGUF · Merlinoz11/Solar-Open2-Apex-GGUF · Baekpica/Solar-Open2-250B-GGUF · nota-ai/Solar-Open2-250B-Nota-NVFP4 · nota-ai/Solar-Open2-250B-Nota-NVFP4-GlobalPruned
Benchmark results
Epoch AI has not published results for Solar Open2 250B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: upstage/Solar-Open2-250B
More from Upstage
Solar Mini 4 · Solar Pro 4 · solar-pro3 · Solar Open 100B · solar-pro2