Qwen3-Coder 30B A3B

Not independently scored by Artificial Analysis

A Mixture-of-Experts coder — 30B total but only ~3B active per token, so it runs faster than its size suggests while all experts must still sit in VRAM. Purpose-built for agentic / tool-use coding.

HumanEval pass@1 98% (39/40), via OpenRouter. Measured by us on this hardware, as a rough sanity check — HumanEval is a different, easier, partly-contaminated benchmark than Artificial Analysis’ composite, so it is not comparable to the coding-index column.

BigCodeBench-Hard pass@1 42% (14/33), via OpenRouter (also runs locally). The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability.

~40 tok/s on RTX 4060 Ti, measured by us. Q4_K_M on an RTX 4060 Ti; 18 GB spills past 16 GB so it partly offloads, but the A3B MoE keeps it fast.

All 30B of experts load into VRAM (~19 GB at Q4) even though only 3B compute — budget for the full size, not the active params. Use YaRN for context beyond its native window. Pairs well with an agent harness (opencode, Cline).