Runs on ≤32 GB · Hugging Face ↗
Coding index 36.5 (Artificial Analysis)
Cohere's first fully-open model — 30B total / ~3B active MoE, Apache-2.0, tuned for agentic SWE. AA coding index 33.4, said to top Devstral 2 (123B) and Nemotron 3 Super (120B). Free on OpenRouter and in opencode Zen's free set.
BigCodeBench-Hard pass@1 35% (42/121), via OpenRouter :free route (hosted) — comparable full-148. 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. First-party BCB-Hard via the free hosted route — lands with the strongest local coders, above what its AA index (33.4) would predict.
No GGUF build yet — ~18 GB estimated at 4-bit from the parameter count. Run from safetensors (transformers / vLLM / SGLang).
~18 GB at Q4 — a 24 GB+ card or a single H100 FP8. But it's free on OpenRouter :free and opencode Zen, which is how we measured it.