Leaderboard / Nanbeige (Kanzhun)
Nanbeige4.2 3B
Nanbeige (Kanzhun) · Nanbeige4 · released 2026-07-21 · data checked 2026-11-01
Nanbeige4.2 3B is a 4.2B-parameter dense model from Nanbeige (Kanzhun) (China), released 2026-07-21 under the Apache-2.0 license. It scores 70.4 on the Small LM Index, #1 of 21 tiny models. It needs about 3.8 GB of memory at 4-bit with an 8K-token context.
Vendor-reported scores, unusually high for its size; treat with care until independently reproduced. Named 3B (non-embedding), 4.2B in total.
Benchmarks
Each bar shows this model's score. The tick marks the best tiny model on that benchmark. Sources: 7 reported by Nanbeige (Kanzhun). How we label sources.
Not reported: estimated
What the index model expects from this model's other scores. Not a measurement.
Specifications
- Lab
- Nanbeige (Kanzhun) (CN · China)
- Architecture
- Dense transformer
- Total parameters
- 4.2B
- Active parameters
- All (dense)
- Size class
- Tiny
- Context window
- 262K tokens
- Input modalities
- text
- Reasoning
- Reasoning (thinking)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~3.8 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 120.3K downloads (30 days) · 857 likes
Compare with
- Nanbeige4.2 3B vs Spark-X2.6 4B (4.1B, index 67.5)
- Nanbeige4.2 3B vs Spark-X2.5 4B (4.1B, index 65.5)
- Nanbeige4.2 3B vs Gemma 3 4B (4.3B, index 17.5)
- Nanbeige4.2 3B vs Qwen3.5 4B (4B, index 57.8)
- Nanbeige4.2 3B vs Gemma 4 E2B (5.1B, index 31.9)
- Nanbeige4.2 3B vs Gemma 3n E2B (5.4B, index 14.3)
Ranked in
- #10 in Best small open models for coding
- #1 in Best LLMs that run on an 8 GB GPU or laptop
- #1 in Best LLMs that run on a 16 GB GPU
- #8 in Best LLMs for a 24 GB GPU (RTX 4090, RTX 3090)
- #1 in Best tiny LLMs for phones and edge devices
- #8 in Best open models with an Apache 2.0 or MIT license
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
vllm serve Nanbeige/Nanbeige4.2-3BMemory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 256K context |
|---|---|---|---|
| 16-bit F16 | 9.3 GB | 12 GB | 33 GB |
| 8-bit Q8_0 | 5.4 GB | 8.0 GB | 29 GB |
| 4-bit Q4_K_M | 3.5 GB | 6.1 GB | 27 GB |