Nanbeige 16B Base 32K needs about 18.1 GB of memory at Q4_K_M (a 9.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 6.6 GB (Q2_K) to 16.8 GB (Q8_0).
Nanbeige 16B Base 32K – 15.8B parameter Llama model
Nanbeige 16B Base 32K is a 15.8B parameter Llama architecture model. It supports a 4096 token context window and is available in multiple GGUF quantisations. The model is licensed under apache-2.0.
Good at
- Coding assistance
- Text generation
- Contextual responses
Limits
- No vision support
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Local code generation
- Chatbot development
- Educational tutoring
Who it’s for. Developers and researchers who need a lightweight Llama model for local inference. The model is suitable for users with GPU or CPU resources who prefer open‑source licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.6 GB | 11.2 GB | Too big | Get file → | |
| Q3_K_S | 6.9 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_M | 7.7 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_L | 8.5 GB | 13.0 GB | Too big | Get file → | |
| Q4_0 | 9.0 GB | 13.5 GB | Too big | Get file → | |
| Q4_K_S | 9.0 GB | 13.6 GB | Too big | Get file → | |
| Q4_K_M | 9.6 GB | 14.1 GB | Too big | Get file → | |
| Q5_0 | 10.9 GB | 15.5 GB | Too big | Get file → | |
| Q5_K_S | 10.9 GB | 15.5 GB | Too big | Get file → | |
| Q5_K_M | 11.2 GB | 15.8 GB | Too big | Get file → | |
| Q6_K | 13.0 GB | 17.5 GB | Too big | Get file → | |
| Q8_0 | 16.8 GB | 21.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (8.99 GB file, ~17.5 GB memory). For 12 GB VRAM, Q5_0 (10.93 GB file, ~19.5 GB memory). For 16 GB VRAM, Q6_K (12.99 GB file, ~21.5 GB memory). Estimates are approximate.
What GPU do you need for Nanbeige 16B Base 32K?
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: the best quant that fits is Q3_K_S (6.9 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (13.0 GB file, about 21.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (16.8 GB file, about 25.4 GB in use).
Which Nanbeige 16B Base 32K quant should you choose?
Q4_K_M is the usual starting point for Nanbeige 16B Base 32K: it balances file size and quality well. Here it is a 9.6 GB file.
The Q8_0 file is 16.8 GB, about 1.8 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.
If memory is tight, the smallest file is Q2_K at 6.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nanbeige 16B Base 32K
How much VRAM does Nanbeige 16B Base 32K need?
About 18.1 GB at Q4_K_M with an 8K context window. That is the 9.6 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 Nanbeige 16B Base 32K on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nanbeige 16B Base 32K GGUF?
It depends on the quant: Q2_K is 6.6 GB, Q3_K_S is 6.9 GB, Q3_K_M is 7.7 GB, Q3_K_L is 8.5 GB, Q4_0 is 9.0 GB, Q4_K_S is 9.0 GB and 6 more.
What context length does Nanbeige 16B Base 32K support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 8.1 GB at 8K and 4.0 GB at 4K.
Where can I download Nanbeige 16B Base 32K GGUF?
The files are on Hugging Face in the TheBloke/Nanbeige-16B-Base-32K-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 Nanbeige 16B Base 32K 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 Nanbeige 16B Base 32K on 8 GB VRAM?
Use the Q4_0 quantisation; it requires about 17.5 GB of VRAM at 8k context, so 8 GB is insufficient.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.