Model Spend Arena2ND ED.
118B · MoE · 1,048,576 ctx · 2026-08-14

Laguna S 2.1

Runs on Data centre · Hugging Face ↗

vLLMSGLangllama.cpp

Not independently scored by Artificial Analysis

The 118B middle Laguna from Poolside (~8B active MoE), open-weight and built for agentic long-horizon coding — the bigger sibling of Laguna XS.2, reported to beat rivals 10x its size. Free on OpenRouter (laguna-s-2.1:free) and opencode Zen.

Sizes on disk

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

QuantizationSize
Q2_K39.7 GB
Q3_K_M54.0 GB
IQ4_XS57.6 GB
Q4_K_S68.6 GB
MXFP471.1 GB
Q4_K_M73.1 GB
Q473.4 GB
Q5_K_M87.9 GB
Q8_0125.0 GB
Q8128.1 GB
Q6_K205.0 GB
BF16235.2 GB

Config tips

~70 GB at Q4 — a single 80 GB card or a DGX Spark. But it's free on OpenRouter :free and opencode Zen, so try it hosted first.