Nanbeige4.3 33B NVFP4 needs about 22.1 GB of memory at its main file (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 18.2 GB to 25.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.0 GB.
Nanbeige4.3 33B NVFP4 – a 33B Llama‑arch teacher model
Nanbeige4.3 33B NVFP4 is a 33.1B parameter Llama model designed for agentic tasks. It supports reasoning and tool use. The model is released under Apache‑2.0 and has a native context of 512K tokens.
Good at
- Agentic reasoning
- Tool integration
- Complex coding
Limits
- 512K context only
- No vision support
- Large VRAM requirement
Best for
- Agentic coding workflows
- Tool‑driven automation
- Large‑context reasoning
Who it’s for. Developers and researchers needing a high‑capacity teacher model for agentic applications. The model is suitable for building smaller distilled agents.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 18.2 GB | 20.4 GB | Too big | Get file → | |
| — | 18.7 GB | 21.0 GB | Too big | Get file → | |
| — | 19.5 GB | 21.8 GB | Too big | Get file → | |
| — | 19.8 GB | 22.1 GB | Too big | Get file → | |
| — | 20.7 GB | 22.9 GB | Too big | Get file → | |
| — | 22.1 GB | 24.3 GB | Too big | Get file → | |
| — | 25.1 GB | 27.4 GB | Too big | Get file → |
For 8‑GB VRAM, use the 18.2 GB file (est. 20.4 GB memory at 8K context). For 12‑GB VRAM, the 19.54 GB file (est. 21.8 GB) is a good balance. For 16‑GB VRAM, the 22.08 GB file (est. 24.3 GB) fits comfortably. Estimates are approximate.
What GPU do you need for Nanbeige4.3 33B NVFP4?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (20.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (25.1 GB file, about 27.4 GB in use).
Which Nanbeige4.3 33B NVFP4 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 18.2 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 Nanbeige4.3 33B NVFP4
How much VRAM does Nanbeige4.3 33B NVFP4 need?
About 22.1 GB at its main file with an 8K context window. That is the 19.8 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 Nanbeige4.3 33B NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nanbeige4.3 33B NVFP4 GGUF?
It depends on the quant: file is 18.2 GB, file is 18.7 GB, file is 19.5 GB, file is 19.8 GB, file is 20.7 GB, file is 22.1 GB and 1 more.
What context length does Nanbeige4.3 33B NVFP4 support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.7 GB at 8K and 7.0 GB at 32K.
Where can I download Nanbeige4.3 33B NVFP4 GGUF?
The files are on Hugging Face in the esatapedico/Nanbeige4.3-33B-NVFP4-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 Nanbeige4.3 33B NVFP4 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 Nanbeige4.3 33B NVFP4 on 8 GB VRAM?
The smallest file is 18.2 GB, which requires about 20.4 GB of VRAM at 8K context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model has no vision support.
What license does the model use?
The model is released under the Apache‑2.0 license.