SU

Sugma4B

SugmaGGUF by hardlyworkingUpdated 2025-05-04
Download on Hugging Face
Parameters4.02B
Context32K
Layers36
Architectureqwen3
Smallest quant3.3 GB
Quick answer

Sugma4B needs about 5.0 GB of memory at Q6_K (a 3.3 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 4.8 GB.

Sugma4B is a 4.02B-parameter Sugma model in GGUF format, quantized by hardlyworking. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.3 GB (Q6_K) to 3.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K3.3 GB 5.0 GB
Fits Get file →

What GPU do you need for Sugma4B?

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 Q6_K (3.3 GB file, about 5.0 GB in use).

Which Sugma4B quant should you choose?

Q6_K (3.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized byhardlyworking
FamilySugma
Licenseapache-2.0
Downloads (HF)20
Last updated2025-05-04

Frequently asked questions about Sugma4B

How much VRAM does Sugma4B need?

About 5.0 GB at Q6_K with an 8K context window. That is the 3.3 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 Sugma4B on an 8 GB GPU?

Yes, with Q6_K: the 3.3 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sugma4B GGUF?

It depends on the quant: Q6_K is 3.3 GB.

What context length does Sugma4B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Sugma4B GGUF?

The files are on Hugging Face in the hardlyworking/Sugma4B-Q6_K-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 Sugma4B 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.

Other GGUFs of Sugma4B

Similar models

Browse all →

More from hardlyworking

All by hardlyworking →

More Sugma models

All Sugma →

Other small models

All small models →