NA

NANBEIGE4.2 3B DSPARK

NanbeigeGGUF by SUPEROXIDESUpdated 2026-09-01
Download on Hugging Face
Parameters848M
Context256K
Layers5
Architecturedflash
Smallest quant0.5 GB
Quick answer

NANBEIGE4.2 3B DSPARK needs about 1.2 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.5 GB (Q4_0) to 1.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

NANBEIGE4.2 3B DSPARK is a 848M-parameter Nanbeige model in GGUF format, quantized by SUPEROXIDES. Its trained context length is 256K tokens. The repository has 6 quant files, from 0.5 GB (Q4_0) to 1.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.5 GB 1.1 GB
Fits Get file →
Q4_K_M0.5 GB 1.2 GB
Fits Get file →
Q6_K0.7 GB 1.4 GB
Fits Get file →
Q8_00.9 GB 1.6 GB
Fits Get file →
BF161.7 GB 2.4 GB
Fits Get file →
F161.7 GB 2.4 GB
Fits Get file →

What GPU do you need for NANBEIGE4.2 3B DSPARK?

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 BF16 (1.7 GB file, about 2.4 GB in use).

Which NANBEIGE4.2 3B DSPARK quant should you choose?

Q4_K_M is the usual starting point for NANBEIGE4.2 3B DSPARK: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.9 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 Q4_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters848M
Layers5
Trained context262,144 tokens
KV cache (fp16)20 KB per token

Source

Quantized bySUPEROXIDES
FamilyNanbeige
Licenseapache-2.0
Downloads (HF)323
Last updated2026-09-01

Frequently asked questions about NANBEIGE4.2 3B DSPARK

How much VRAM does NANBEIGE4.2 3B DSPARK need?

About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.5 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 NANBEIGE4.2 3B DSPARK on an 8 GB GPU?

Yes, with BF16: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NANBEIGE4.2 3B DSPARK GGUF?

It depends on the quant: Q4_0 is 0.5 GB, Q4_K_M is 0.5 GB, Q6_K is 0.7 GB, Q8_0 is 0.9 GB, BF16 is 1.7 GB, F16 is 1.7 GB.

What context length does NANBEIGE4.2 3B DSPARK support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.

Where can I download NANBEIGE4.2 3B DSPARK GGUF?

The files are on Hugging Face in the SUPEROXIDES/NANBEIGE4.2_3B_DSPARK_-_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 NANBEIGE4.2 3B DSPARK 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.

Similar models

Browse all →

More from SUPEROXIDES

All by SUPEROXIDES →

More Nanbeige models

All Nanbeige →

Other tiny models

All tiny models →