Nanbeige4.3 33B Base needs about 22.3 GB of memory at Q4_K_M (a 20.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 27.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.0 GB.
Nanbeige4.3 33B Base – a 33.1B‑parameter teacher model
Nanbeige4.3 33B Base is a 33.1B‑parameter llama architecture model trained on 131072 context tokens. It is released under the apache‑2.0 license and serves as the flagship teacher for the Nanbeige4.3 series.
Good at
- Complex coding
- Professional cowork tasks
- Agentic performance
Limits
- No vision support
- Requires large VRAM for higher quants
- No mixture of experts
Best for
- Post‑training for domain agents
- Real‑world deployment of large‑scale LLMs
- Benchmarking against 30B models
Who it’s for. Developers and researchers building or fine‑tuning large‑scale language models. The model is suitable for teams needing a high‑capacity teacher for distillation pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.3 GB | Fits | Get file → | |
| IQ1_S | 7.7 GB | 9.9 GB | Too big | Get file → | |
| IQ1_M | 8.3 GB | 10.5 GB | Too big | Get file → | |
| IQ2_XXS | 9.3 GB | 11.6 GB | Too big | Get file → | |
| IQ2_XS | 10.2 GB | 12.5 GB | Too big | Get file → | |
| IQ2_S | 10.8 GB | 13.1 GB | Too big | Get file → | |
| IQ2_M | 11.7 GB | 13.9 GB | Too big | Get file → | |
| Q2_K_S | 11.8 GB | 14.0 GB | Too big | Get file → | |
| Q2_K | 12.7 GB | 14.9 GB | Too big | Get file → | |
| IQ3_XXS | 13.1 GB | 15.4 GB | Too big | Get file → | |
| IQ3_XS | 14.0 GB | 16.3 GB | Too big | Get file → | |
| Q3_K_S | 14.7 GB | 16.9 GB | Too big | Get file → | |
| IQ3_S | 14.8 GB | 17.0 GB | Too big | Get file → | |
| IQ3_M | 15.2 GB | 17.5 GB | Too big | Get file → | |
| Q3_K_M | 16.3 GB | 18.5 GB | Too big | Get file → | |
| Q3_K_L | 17.6 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 18.0 GB | 20.3 GB | Too big | Get file → | |
| Q4_0 | 19.0 GB | 21.2 GB | Too big | Get file → | |
| Q4_K_S | 19.1 GB | 21.3 GB | Too big | Get file → | |
| Q4_K_M | 20.1 GB | 22.3 GB | Too big | Get file → | |
| Q4_1 | 20.9 GB | 23.2 GB | Too big | Get file → | |
| Q5_K_S | 22.9 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_M | 23.5 GB | 25.7 GB | Too big | Get file → | |
| Q6_K | 27.2 GB | 29.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 7.66 GB, memory 9.9 GB at 8k context). For 16 GB VRAM, IQ2_XS (10.25 GB, 12.5 GB). For 24 GB VRAM, Q4_K_M (20.05 GB, 22.3 GB). Memory estimates are approximate.
What GPU do you need for Nanbeige4.3 33B 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 the main file (0.0 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (9.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (13.1 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (20.9 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.2 GB file, about 29.4 GB in use).
Which Nanbeige4.3 33B Base quant should you choose?
Q4_K_M is the usual starting point for Nanbeige4.3 33B Base: it balances file size and quality well. Here it is a 20.1 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 Nanbeige4.3 33B Base
How much VRAM does Nanbeige4.3 33B Base need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.1 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 Base on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nanbeige4.3 33B Base GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.7 GB, IQ1_M is 8.3 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.2 GB, IQ2_S is 10.8 GB and 18 more.
What context length does Nanbeige4.3 33B 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 1.7 GB at 8K and 7.0 GB at 32K.
Where can I download Nanbeige4.3 33B Base GGUF?
The files are on Hugging Face in the mradermacher/Nanbeige4.3-33B-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 Nanbeige4.3 33B 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 Nanbeige4.3 33B Base on 8 GB VRAM?
Use the IQ1_S quant; it requires about 9.9 GB of VRAM at 8k 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.