Nanbeige4 3B Thinking 2511 needs about 3.5 GB of memory at Q4_K_M (a 2.4 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 7.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Nanbeige4 3B Thinking 2511 – a compact reasoning‑focused LLM
Nanbeige4 3B Thinking 2511 is a 3.93 billion‑parameter llama model trained on 65536 context tokens. It excels at reasoning tasks and function‑calling. The model is released under apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Reasoning
- Function‑calling
- Creative writing
Limits
- No vision support
- Requires 8 k context for memory estimates
- Potential for harmful content
Best for
- Chatbots needing reasoning
- Tool‑using agents
- Creative writing assistants
Who it’s for. Developers building lightweight reasoning agents or chat applications that need reliable function‑calling. The model is suitable for projects that can run on consumer GPUs with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 2.5 GB | Fits | Get file → | |
| Q2_K | 1.6 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XXS | 1.7 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XS | 1.8 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ3_M | 1.9 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 3.1 GB | Fits | Get file → | |
| Q2_K_L | 2.0 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 3.2 GB | Fits | Get file → | |
| IQ4_XS | 2.2 GB | 3.3 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 2.3 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_XL | 2.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_1 | 2.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_L | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_L | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q6_K_L | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q8_0 | 4.2 GB | 5.2 GB | Fits | Get file → | |
| BF16 | 7.9 GB | 8.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (file size 1.51 GB, memory 2.5 GB) or Q2_K (1.62 GB, 2.7 GB). For 12 GB VRAM, Q4_K_M (2.02 GB, 3.1 GB) or Q5_K_M (2.83 GB, 3.9 GB) are good choices. Higher‑quality quants like Q8_0 (4.18 GB, 5.2 GB) require 16 GB or more.
What GPU do you need for Nanbeige4 3B Thinking 2511?
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 Q5_K_M (2.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.9 GB file, about 8.9 GB in use).
Which Nanbeige4 3B Thinking 2511 quant should you choose?
Q4_K_M is the usual starting point for Nanbeige4 3B Thinking 2511: it balances file size and quality well. Here it is a 2.4 GB file.
The Q8_0 file is 4.2 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.
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 3B Thinking 2511
How much VRAM does Nanbeige4 3B Thinking 2511 need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.4 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 3B Thinking 2511 on an 8 GB GPU?
Yes, with Q8_0: the 4.2 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nanbeige4 3B Thinking 2511 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.5 GB, Q2_K is 1.6 GB, IQ3_XXS is 1.7 GB, IQ3_XS is 1.8 GB, Q3_K_S is 1.9 GB and 19 more.
What context length does Nanbeige4 3B Thinking 2511 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Nanbeige4 3B Thinking 2511 GGUF?
The files are on Hugging Face in the bartowski/Nanbeige_Nanbeige4-3B-Thinking-2511-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 3B Thinking 2511 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 this model on 8 GB VRAM?
Yes, using IQ2_M or Q2_K quants will fit within 8 GB VRAM with approximate 2.5–2.7 GB memory usage.
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.