Nanbeige4.2 3B needs about 4.6 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.6 GB (Q4_K_M) to 4.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.9 GB.
Nanbeige4.2 3B – compact agentic model with strong reasoning
Nanbeige4.2 3B is a 4.17 B parameter model built on a LoopSplit transformer. It delivers solid agentic behavior and reasoning across mathematical, coding, and scientific tasks. The model supports a 262,144‑token context and is Apache‑2.0 licensed.
Good at
- Agentic tool‑use
- Mathematical reasoning
- Code generation
Limits
- No vision support
- Requires llama.cpp patch for nanbeige architecture
- Large context needs 44 KV‑cache slots
Best for
- Personal assistant workflows
- Office automation
- Research support
Who it’s for. Developers and researchers who need a small, local LLM with strong agentic and reasoning capabilities. The model is suitable for CPU‑only inference with the appropriate llama.cpp patch.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.6 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 4.4 GB | 6.4 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (2.57 GB file, ~4.6 GB memory at 8 k context). For 12 GB VRAM, use Q8_0 (4.43 GB file, ~6.4 GB memory at 8 k context). Memory estimates are approximate.
What GPU do you need for Nanbeige4.2 3B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.6 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 6.4 GB in use).
Which Nanbeige4.2 3B quant should you choose?
Q4_K_M is the usual starting point for Nanbeige4.2 3B: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nanbeige4.2 3B
How much VRAM does Nanbeige4.2 3B need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 2.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Nanbeige4.2 3B on an 8 GB GPU?
Yes, with Q8_0: the 4.4 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nanbeige4.2 3B GGUF?
It depends on the quant: Q4_K_M is 2.6 GB, Q8_0 is 4.4 GB.
What context length does Nanbeige4.2 3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.5 GB at 8K and 5.9 GB at 32K.
Where can I download Nanbeige4.2 3B GGUF?
The files are on Hugging Face in the Tdamre/Nanbeige4.2-3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nanbeige4.2 3B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Nanbeige4.2 3B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.6 GB of VRAM at 8 k context, fitting within an 8 GB budget.
Does the model support vision tasks?
No, the model has no vision capabilities.
What patch is needed for llama.cpp?
Apply the nanbeige architecture patch to load the model correctly.