Model Spend Arena2ND ED.
250B · MoE · 1,048,576 ctx · 2026-08-14

Solar Open2 250B

Runs on Data centre · Hugging Face ↗

vLLMSGLangllama.cpp

Coding index 44.7 (Artificial Analysis)

Upstage's 250B-total MoE (320 experts, 1M context) — the Korean lab's first frontier-scale open release, trending on HF but not yet on the AA index.

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈6 GB at 32K, fp16).

QuantizationSize
Q2_K95.4 GB
IQ4_XS136.2 GB
Q6_K205.6 GB

Config tips

~140 GB at Q4 — a 2×80 GB node, or heavy CPU offload with a community GGUF on llama.cpp. All 320 experts must be resident despite the small per-token compute.