2 models across 1 family · Latest: Nanbeige4.1-3B (2026-02)
Massive multilingual model, open-source focus.
Nanbeige LLM Lab's portfolio covers 2 active models across 1 non-obsolete family, with task labels spanning rag, agents, and long context. Open a model detail page to compare provider routes and sourced benchmarks.
Portfolio context: 4 decision-task tags, 2 active tracked models, latest research stamp 2026-05-19.
Use this portfolio page for
- Teams evaluating rag, agents, and long context across this lab's releases
- Readers comparing families before locking a flagship SKU
- 2 tracked SKUs for migration and pricing follow-ups
Do not stop here for
- Choosing a hosting provider without opening a model page for price ladders
Active models
2
Non-deprecated SKUs linked to this researcher
Active families
1
Non-obsolete families in coverage
Open catalog
2 OSS
0 open-weight (text match)
Decision task tags
4
Mapped to the site-wide task taxonomy
Latest dated release
2026-02-11
Nanbeige4.1-3B
Freshness
2026-05-19
Researched 16d ago
Release cadence
Showing 2 recent dated ships (full timeline below). Latest spotlight: Nanbeige4.1-3B (2026-02-11).
Where this lab wins
- RAG: 1 tracked model with ruler / needle retrieval benchmarks.
- Agentic: 1 tracked model with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 1 tracked model with context-token or InfiniteBench-class signal.
- JSON/tool-use: 1 tracked model with BFCL / Nexus strict-JSON routing coverage.
Flagship quality / price signal
Anchor SKU: Nanbeige4-3B (best sourced coding Q/$ in this portfolio).
Quality / dollar unavailable for this anchor — missing benchmark coverage and/or output token price on the cheapest ladder route (open the model detail after pricing lands).
Nanbeige LLM Lab is a Chinese AI research lab founded in 2023. Massive multilingual model, open-source focus. Nanbeige LLM Lab ships 1 model family totaling 2 models, with the most recent release Nanbeige4.1-3B in 2026-02. Notable families include Nanbeige4. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added. Researchers and evaluators can. View official API endpoints, benchmark performance, and coding/agent fit for every Nanbeige LLM Lab model.
About
Nanbeige LLM Lab is the AI research team at BOSS Zhipin (Kanzhun Limited), Beijing’s leading online recruitment platform, known for its commitment to open-sourcing powerful multilingual large language models. Despite being a relatively new entrant in this field, the lab has swiftly established itself as a notable open-source contributor through GitHub and Hugging Face. A focal point of the lab’s innovation is the Nanbeige-16B model, a 16-billion parameter LLM trained on an extensive dataset encompassing 2.5 trillion tokens drawn from internet corpora, books, and code. The model is available in Base, Chat, and extended-context variants (Base-32k and Chat-32k), making it versatile for general-purpose and conversational applications. Nanbeige LLM Lab distinguishes itself by maintaining a transparent and accessible approach. Unlike many counterparts that restrict access, Nanbeige shares its models and resources freely. The lab provides detailed documentation with inference code and fine-tuning scripts, and publishes transparent benchmarking results using tools like LLMEval-3 across C-Eval, CMMLU, and MMLU. The lab has continued iterating with the Nanbeige2 series (Nanbeige2-8B-Chat) and more recently the Nanbeige4 family, including Nanbeige4-3B and Nanbeige4.1-3B — compact models with strong reasoning and agentic capabilities. These models are developed using supervised fine-tuning and direct preference optimization, reflecting the lab’s expertise in efficient model alignment.
Featured models
| Model | Released | Context | Input price ($/1M) | Output price ($/1M) | License |
|---|---|---|---|---|---|
| Nanbeige4.1-3B | 2026-02-11 | 256k | - | - | Open Source |
| Nanbeige4-3B | 2025-12-13 | 64k | - | - | Open Source |
Model families
Recent releases
- Nanbeige4.1-3B- 2026-02-11
- Nanbeige4-3B- 2025-12-13
FAQ
Who founded Nanbeige LLM Lab and when?
Nanbeige LLM Lab was founded in 2023 and is associated with Beijing, China.
What models has Nanbeige LLM Lab released?
Nanbeige LLM Lab ships 2 models across 1 family: Nanbeige4.
Is Nanbeige LLM Lab's technology open source?
All tracked models are released under Open Source.
Where is Nanbeige LLM Lab headquartered?
Nanbeige LLM Lab is headquartered in Beijing, China.
What is Nanbeige LLM Lab known for?
Massive multilingual model, open-source focus. Its most prominent tracked family is Nanbeige4.
How can I access Nanbeige LLM Lab's models?
Nanbeige LLM Lab's provider availability is tracked on model pages as API and hosting data is verified.
Explore related pages
Last reviewed: 2026-05-19. Data sourced from public lab announcements and provider documentation.