gpt-oss-120b
the only genuinely capable model here that fits on a single 80gb card, under clean apache 2.0.
nearly a year old and still the most practical self-host on this list — one card, no licence questions, real agentic ability.
openai's open-weight release carries unmodified apache 2.0. the only restrictions are apache's own patent-litigation termination clause and ordinary trademark limits; a separate usage policy exists but is explicitly not part of the licence and imposes nothing contractual. after the licences elsewhere in this category, that plainness is worth something.
the practical case is the footprint. 117b total with only 5.1b active per token means it fits a single 80gb gpu at native mxfp4 — roughly 60gb of weights with room left for kv cache — and the small active path makes cpu and consumer-gpu inference viable at lower throughput. nothing else here with real agentic and tool-calling ability runs on one card.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- open-weight llms
- pricing
- free (apache 2.0)
- website
- huggingface.co
nearly a year old and still the most practical self-host on this list — one card, no licence questions, real agentic ability.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.