DE

Nanbeige4.1 3B

DeepSeekGGUF by RoroMachine14Updated 2026-05-15
Download on Hugging Face
Parameters3.93B
Context256K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

Nanbeige4.1 3B needs about 5.2 GB of memory at Q8_0 (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Nanbeige4.1 3B – compact reasoning and agentic model

Nanbeige4.1 3B is a 3.93‑billion‑parameter llama model fine‑tuned for reasoning, preference alignment, and deep‑search agentic tasks. It supports structured reasoning, code generation with step‑by‑step explanation, and tool use.

Good at

  • Reasoning across math, code, science
  • Deep‑search with many tool invocations
  • Preference‑aligned responses

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is apache‑2.0

Best for

  • Small‑scale reasoning applications
  • Agentic tool‑use workflows
  • Educational coding assistants

Who it’s for. Developers and researchers needing a lightweight model that balances reasoning and agentic capabilities. It runs on consumer hardware via llama.cpp or transformers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.2 GB 5.2 GB
Fits Get file →

The Q8_0 quant is 4.18 GB and needs about 5.2 GB of VRAM at 8k context. For 8 GB VRAM, Q8_0 is suitable. If VRAM is lower, no other quant is available in the file list.

What GPU do you need for Nanbeige4.1 3B?

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: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).

Which Nanbeige4.1 3B quant should you choose?

Q8_0 (4.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.93B
Layers32
Trained context262,144 tokens
KV cache (fp16)64 KB per token

Source

Quantized byRoroMachine14
FamilyDeepSeek
Licenseapache-2.0
Downloads (HF)992
Last updated2026-05-15

Frequently asked questions about Nanbeige4.1 3B

How much VRAM does Nanbeige4.1 3B need?

About 5.2 GB at Q8_0 with an 8K context window. That is the 4.2 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 Nanbeige4.1 3B 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 Nanbeige4.1 3B GGUF?

It depends on the quant: Q8_0 is 4.2 GB.

What context length does Nanbeige4.1 3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Nanbeige4.1 3B GGUF?

The files are on Hugging Face in the RoroMachine14/nanbeige-4.1-3b-deepseek-distilled repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nanbeige4.1 3B 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 Nanbeige4.1 3B on 8 GB VRAM?

Yes, the Q8_0 quant uses about 5.2 GB of VRAM at 8k context, fitting within an 8 GB budget.

Does this model support vision?

No, the model has no vision capability.

What license applies?

The model is released under the apache‑2.0 license.

Other GGUFs of Nanbeige4.1-3B

Similar models

Browse all →

More DeepSeek models

All DeepSeek →

Other small models

All small models →