{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-10-24-nanbeige4-3-33b-open-weights/","md":"https://postcutoff.com/e/2026-10-24-nanbeige4-3-33b-open-weights/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-24-nanbeige4-3-33b-open-weights","date":"2026-10-24","date_precision":"day","short_title":"BOSS Zhipin's Nanbeige team open-sources Nanbeige4.3-33B, a 512K-context agentic coding model under Apache 2.0","deck":null,"takeaway":"On Oct 24, 2026 the Nanbeige team at Kanzhun (operator of China's BOSS Zhipin recruitment platform) published Nanbeige4.3-33B and its base model on Hugging Face under Apache 2.0.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Hugging Face: Nanbeige/Nanbeige4.3-33B model card","url":"https://huggingface.co/Nanbeige/Nanbeige4.3-33B","type":"official","group":"primary","domain":"huggingface.co"},{"n":2,"title":"Pandaily: BOSS Zhipin's Nanbeige team open-sources Nanbeige4.3-33B (Oct 26)","url":"https://pandaily.com/nanbeige4-3-33b-open-source-agent-coding-model-512k-context-apache-2-boss-zhipin","type":"press","group":"press","domain":"pandaily.com"}],"official":1,"filed":"2026-10-26","updated":"2026-10-26","orgs":["Kanzhun","Nanbeige"],"title":"BOSS Zhipin's Nanbeige team open-sources Nanbeige4.3-33B, a 512K-context agentic coding model under Apache 2.0","summary":"On Oct 24, 2026 the Nanbeige team at Kanzhun (operator of China's BOSS Zhipin recruitment platform) published Nanbeige4.3-33B and its base model on Hugging Face under Apache 2.0. The ~33B model has a 512K-token context and is tuned for coding agents and office tasks; the team reports it beats Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B on most agentic benchmarks it ran, figures not yet checked independently. It is meant as a teacher for distilling agent skills into smaller models such as a planned 3B.","key_facts":["Hugging Face repos Nanbeige/Nanbeige4.3-33B and -Base created Oct 24, 2026; Apache 2.0 (commercial use allowed); ~33.1B parameters","Context window 524,288 tokens (512K); enable_thinking / preserve_thinking switches; XML or JSON tool calls","Team comparison against Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B at highest thinking effort with the same harness: Terminal-Bench 2.1 and 4.0, SWE-Atlas-QnA, NL2Repo, DeepSWE, Automation Bench, Toolathlon-Verified, EnterpriseOps-Gym, GDPval, Claw-Eval, DeepPlanning, Tau3-Bench; 'leads on most'; on JobBench it beats the baseline in most of 35 occupations (self-reported)","Strategy: a high-capacity teacher agent first, then distillation into small models (a Nanbeige4.3-3B is named)","Pandaily covered it on Oct 26; HF showed ~2.8k downloads and ~590 likes on Oct 26"],"key_numbers":[],"tags":["llm","open-weights","china","coding","agents","apache-2.0"],"science":null,"body_md":"## What happened\n\nA recruitment-platform company's AI team released a mid-sized open model aimed at coding agents rather than chat. Weights for the\ninstruct and base versions went up on Hugging Face under a permissive licence, with serving examples for vLLM and SGLang.\n\n## Why it matters\n\nIt adds a 30B-class Chinese open model with a longer context (512K) than its named rivals. Its benchmark lead over Qwen, Meta and\nGoogle models of similar size is the team's own claim until independent leaderboards test it.","disputed":[],"related":[{"id":"2026-08-10-meta-muse-glimmer-open-weights","url":"https://postcutoff.com/e/2026-08-10-meta-muse-glimmer-open-weights/","date":"2026-08-10","date_precision":"day","short_title":"Meta returns to open weights with Muse Glimmer, a 30B Apache-2.0 agentic model","deck":null,"takeaway":"On 2026-08-10 Meta released Muse Glimmer, a 30B-parameter open-weight model under Apache 2.0, optimized for local, always-on agent workflows and designed to run on a single consumer GPU or Mac.","category":"open-source","category_label":"Open source","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Meta"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"nanbeige4-3-33b","name":"Nanbeige4.3-33B","url":"https://postcutoff.com/m/nanbeige4-3-33b/"}],"changes":[{"date":"2026-10-26","type":"filed","text":"Created (model card read on Hugging Face)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-26","run":null,"sources_read":"Model card read on Hugging Face","updated":"2026-10-26","human_review":null,"version":{"date":"2026-10-27"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":177,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":116,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":207,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":146,"in_training_data":false}],"short_url":null}