Nanbeige4.2 3B Base needs about 3.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 3.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.0 GB.
Nanbeige4.2 3B Base – 4.17B parameter Looped Transformer
Nanbeige4.2 3B Base is a 4.17B parameter model trained from scratch with a Looped Transformer architecture. It improves reasoning and coding performance over earlier Nanbeige models and comparable open‑source bases. The model is released under the apache-2.0 license.
Good at
- Reasoning and math tasks
- Code generation
- Knowledge‑intensive queries
Limits
- No vision support
- Large VRAM required for higher quant levels
- License allows redistribution but not commercial use without permission
Best for
- Academic research on reasoning models
- Small‑to‑medium coding assistants
- Educational tools for STEM subjects
Who it’s for. Researchers and developers who need a high‑quality, open‑source language model for reasoning and coding tasks. The model is suitable for projects that can accommodate its VRAM and RAM requirements and comply with the apache-2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 1.3 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XXS | 1.4 GB | 2.6 GB | Fits | Get file → | |
| IQ2_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ2_S | 1.6 GB | 2.8 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ3_S | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ3_M | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 2.4 GB | 3.6 GB | Fits | Get file → | |
| IQ4_NL | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_S | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q4_1 | 2.7 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_S | 2.9 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_M | 3.0 GB | 4.2 GB | Fits | Get file → | |
| Q6_K | 3.4 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S or IQ1_M (est. 2.4–2.5 GB). For 12 GB VRAM, IQ2_S or Q2_K_S (est. 2.8–2.9 GB). For 24 GB VRAM, Q4_K_M or Q5_K_S (est. 3.8–4.2 GB). Estimates are approximate.
What GPU do you need for Nanbeige4.2 3B Base?
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: the best quant that fits is Q4_1 (2.7 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.4 GB file, about 4.7 GB in use).
Which Nanbeige4.2 3B Base quant should you choose?
Q4_K_M is the usual starting point for Nanbeige4.2 3B Base: it balances file size and quality well. Here it is a 2.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nanbeige4.2 3B Base
How much VRAM does Nanbeige4.2 3B Base need?
About 3.8 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 Base on an 8 GB GPU?
Yes, with Q6_K: the 3.4 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nanbeige4.2 3B Base GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB and 19 more.
What context length does Nanbeige4.2 3B Base support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 3.0 GB at 32K.
Where can I download Nanbeige4.2 3B Base GGUF?
The files are on Hugging Face in the mradermacher/Nanbeige4.2-3B-Base-i1-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 Base 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 Base on 8 GB VRAM?
Yes, using the IQ1_S or IQ1_M quant, which estimate 2.4–2.5 GB of VRAM at 8 k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.