Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model

Nanbeige LLM Lab has released Nanbeige4.3-33B on Hugging Face under the Apache 2.0 license.Nanbeige4.3-33B is a 33B dense language model built for agentic coding and office-style ‘cowork’ tasks.The lab sits inside the recruitment platform BOSS Zhipin.It also published Nanbeige4.

3-33B-Base for custom post-training.The model supports a 524,288-token context window.In the lab’s own table, it leads 17 of 20 benchmarks against 3 open models near 30B.TL;DR Size: 33B parameters, dense (no MoE), 524,288-token (512K) context, BF16 weights.Runs on: Multi-GPU servers.

The card’s SGLang and vLLM recipes use 4-way tensor parallelism.BF16 weights need about 66 GB (our arithmetic).1 community quantization is listed.Performance: Leads 17 of 20 rows in Nanbeige’s own comparison against Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B.Best: 80.9 on Terminal-Bench 2.

1, versus 73.0 for Qwen3.8-27B.Worst: 23.8 on Terminal-Bench 4.0 (its lowest score).It also trails Qwen3.8-27B on SWE-Bench Pro, 60.3 vs 61.7.What is Nanbeige4.3-33B?Nanbeige4.3-33B is the flagship ‘teacher’ model of the Nanbeige4.3 series.

The lab’s stated strategy is to build a strong teacher first.It then plans to distill agentic skills into smaller models, starting with Nanbeige4.3-3B.How is Nanbeige4.3-33B built?The config.json declares a standard LlamaForCausalLM architecture.

There is no expert routing, so all 33B parameters run on every token.

52 layers, hidden size 7,168 56 query heads and 8 key-value heads (grouped-query attention), head dimension 128 FFN intermediate size 22,016, vocabulary of 166,912 tokens RoPE theta of 120,000,000 and 524,288 max positions The chat template exposes 3 controls.

enablethinking toggles reasoning and is on by default.preservethinking keeps reasoning from earlier turns.Nanbeige recommends it for multi-turn tool use and code agents.Passing tools enables tool calling, and an XML call format is recommended.How does Nanbeige4.3-33B perform on benchmarks?

Nanbeige compared the model with Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B.Every model ran at its highest thinking effort, with shared hyperparameters and harnesses.All scores in this section are self-reported.Agentic coding: It scores 80.9 on Terminal-Bench 2.1, against 73.0 for Qwen3.8-27B.

DeepSWE shows the widest gap: 65.5 versus 42.5.On Terminal-Bench 4.0, it scores 23.8 while Gemma4-31B scores 0.0.Agentic cowork: It posts 54.2 on Automation Bench versus 38.3, and 44.8 on JobBench versus 34.5.On YC-bench, simulated earnings reach $1,025,437 versus $641,290.Reasoning: It reports 95.

2 on AIME 2026 and 84.0 on AA-LCR.It loses 3 of 20 rows.Qwen3.8-27B leads SWE-Bench Pro (61.7 vs 60.3) and GDPval (86.4 vs 84.8).Gemma4-31B leads GPQA Diamond in Nanbeige’s table, 91.3 vs 89.5.The Base model beats Gemma4-31B-Base on all 8 reported tasks.Examples include MMLU-Pro (66.9 vs 59.

3) and GPQA (62.0 vs 41.5).BackNext step Auto-play

52layers

56 / 8query / KV heads (GQA)

7,168hidden size

524,288max positions Agentic coding Agentic cowork Reasoning Base model All scores self-reported by Nanbeige on its Hugging Face model cards, at each model's highest thinking effort with shared harnesses. Not independently verified. Context length 131,072 tokens

Concurrent sequences 1

Weights BF16Weights 8-bit

KV cache BF16KV cache FP8

Arithmetic from config.json: 52 layers × 8 KV heads × 128 dims × 2 (K and V) × bytes per value. That is 212,992 bytes (about 208 KiB) per token in BF16. Weights use 33B parameters. Excludes activations and framework overhead. Estimated GPU memory

0 GB Weights

KV cache

Per 80 GB GPU (ideal fit)

The model card's SGLang and vLLM recipes use 4-way tensor parallelism. Row in Nanbeige tableNanbeige listsOfficial card Muse-Glimmer-30B, SWE-Bench Pro36.951.2 (Meta)looks swapped Gemma4-31B, SWE-Bench Pro51.236.9 (Meta-reported)looks swapped Gemma4-31B, GPQA Diamond91.384.3 (Google)conflict Muse-Glimmer-30B, Terminal-Bench 2.161.851.7 (Meta)<td&