OpenAI
OpenAI's current flagship closed model.
OpenAI now ships its own open-weight models (the gpt-oss line), which are by definition the closest openly-runnable relatives of its hosted GPT models. Closest by capability class:
These are community-regarded closest open-weight models by capability class — an editorial judgement, not a benchmark ranking. Sizes and hardware/speed figures are derived from the catalog and the same fit engine used across the site, judged at a 8,192-token context. Speeds are estimates, not measurements.
gpt-oss is OpenAI's own open-weight release — the most defensible "closest local" claim there is, since it shares OpenAI's training lineage rather than merely approximating it.
| Local model | Size | Hardware to run it | Est. speed |
|---|---|---|---|
| gpt-oss-120b openai | 120.4B (MoE) | Runs fully on 96 GB (RTX Pro 6000 Blackwell 96GB) at F16 Runs fully on GPU @ F16 · 8K ctx | 190–253 tok/s (estimate) |
| gpt-oss-20b openai | 21.5B (MoE) | Runs fully on 16 GB (RTX 5060 Ti 16GB) at F16 Runs fully on GPU @ F16 · 8K ctx | 77–103 tok/s (estimate) |
Where gpt-oss is unavailable or too large, the strongest open generalists are the community's next-closest local picks.
| Local model | Size | Hardware to run it | Est. speed |
|---|---|---|---|
| Qwen3.6-35B-A3B Qwen tags: Long context | 36B (MoE) | Runs fully on 24 GB (RTX 4090) at Q4_K_M Runs fully on GPU @ Q4_K_M · 8K ctx | 27–35 tok/s (estimate) |
| Qwen3-32B Qwen | 32.8B | Runs fully on 24 GB (RTX 4090) at Q4_K_M Runs fully on GPU @ Q4_K_M · 8K ctx | 28–37 tok/s (estimate) |
"Hardware to run it" is the smallest single GPU in our roster that runs the model's best-fitting quant fully on GPU at this context, computed by the same fit engine used sitewide. "Est. speed" is a modelled generation-throughput range labelled estimate (D8), never a measurement. Equivalence is a conservative editorial call and no benchmark scores are implied.