SU

Supra2.1 Ultra

SupraGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters230M
Context2K
Layers32
Architecturellama
Smallest quant0.1 GB
Quick answer

Supra2.1 Ultra needs about 0.9 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.5 GB (F16).

230M‑parameter LLaMA model with 8k context

Supra2.1 Ultra is a 0.23‑billion‑parameter LLaMA model trained on 40B tokens. It offers 2048‑token context length and is released under Apache‑2.0. The model is not aligned and has no vision support.

Good at

  • Fast inference on low‑memory GPUs
  • Small footprint for edge deployment
  • Simple LLaMA architecture

Limits

  • No alignment or safety evaluation
  • No vision capabilities
  • Limited to 2048‑token context

Best for

  • Quick prototyping
  • Local chatbot demos
  • Low‑resource inference

Who it’s for. Developers needing a lightweight LLaMA model for local inference. Suitable for experimentation and educational projects where large‑scale safety is not critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
Q3_K_S0.1 GB 0.7 GB
Fits Get file →
Q3_K_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_L0.1 GB 0.7 GB
Fits Get file →
IQ4_XS0.1 GB 0.7 GB
Fits Get file →
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
Q5_K_S0.2 GB 0.7 GB
Fits Get file →
Q5_K_M0.2 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q8_00.2 GB 0.8 GB
Fits Get file →
F160.5 GB 1.0 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.16 GB) or Q5_K_M (0.18 GB) are good choices. If 4 GB VRAM is available, use Q3_K_S (0.12 GB) or Q2_K (0.11 GB). For higher precision, Q8_0 (0.25 GB) or F16 (0.46 GB) can be used on GPUs with 12 GB or more.

What GPU do you need for Supra2.1 Ultra?

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 F16 (0.5 GB file, about 1.2 GB in use).

Which Supra2.1 Ultra quant should you choose?

Q4_K_M is the usual starting point for Supra2.1 Ultra: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.2 GB, about 1.6 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 0.1 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

Architecturellama
Parameters230M
Layers32
Trained context2,048 tokens
KV cache (fp16)32 KB per token

Source

Quantized bymradermacher
FamilySupra
Licenseapache-2.0
Downloads (HF)828
Last updated2026-10-27

Frequently asked questions about Supra2.1 Ultra

How much VRAM does Supra2.1 Ultra need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Supra2.1 Ultra on an 8 GB GPU?

Yes, with F16: the 0.5 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Supra2.1 Ultra GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, IQ4_XS is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.

What context length does Supra2.1 Ultra support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.

Where can I download Supra2.1 Ultra GGUF?

The files are on Hugging Face in the mradermacher/Supra2.1-Ultra-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 Supra2.1 Ultra 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 Supra2.1 Ultra on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_M quantized files; they require about 0.9 GB VRAM at 8k context.

Does the model support vision?

No, Supra2.1 Ultra has no vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Supra models

All Supra →

Other tiny models

All tiny models →