gpt-oss-20b alternatives

verdictthe only genuinely multimodal family that runs at phone scale, now on plain apache 2.0 — the clearest default in this category.

switch foranything that needs to see or hear as well as read, on hardware you already carry.

verdictthe best reasoning-per-gigabyte here and the longest context by a wide margin — just make sure you're downloading the version alibaba actually ships now.

switch forlong-document work on a laptop, where the context window matters more than the parameter count.

verdictthe most institutionally careful entry here — signed weights, plain apache 2.0, dense architecture — and much too new to have a community around it.

switch forregulated environments that need provenance on the weights themselves, not just a permissive licence.

verdictclean mit terms and genuinely good instruction following for 3.8b — held back by being a february 2025 model in a field that has moved twice since.

switch forstructured output and tool calling in a small footprint, where reliability beats novelty.

verdictpunches above its size on instruction following and comes from the one vendor here whose whole reason for existing is openness — with weaker long-context recall than the spec suggests.

switch forinstruction-following and tool use at 3b, and anyone who values a transparent training story.

verdictgenuinely fast for its capacity and the only entry here with a revenue cap — phrased permissively enough that a growing company could sail past it without noticing.

switch forsmall companies and individuals who want moe speed on a laptop and will stay well under the threshold.

verdictimpressive engineering — a hybrid mamba architecture built for machines without gpus — attached to the most conditional licence in this ranking.

switch forcpu-only edge deployment where a long context matters and the licence terms are acceptable.