SU

SU 01

GGUFGGUF by axi0mXUpdated 2026-05-24
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3moe
Smallest quant10.3 GB
Quick answer

SU 01 needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 17 quants, from 10.3 GB (IQ2_XXS) to 61.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

30B-A3B reasoning model for olympiad problem solving

SU‑01 is a 30.5B‑parameter model trained for rigorous mathematical and scientific reasoning. It uses a post‑training recipe to produce long‑horizon proofs without external tools. The model supports up to 262,144‑token context.

Good at

  • Olympiad reasoning
  • Long‑horizon proof generation
  • Multi‑step problem solving

Limits

  • No vision support
  • Requires large VRAM for higher quantizations
  • License is apache‑2.0

Best for

  • Competitive math contests
  • Scientific proof tasks
  • Complex reasoning queries

Who it’s for. Researchers and educators needing a specialized reasoning model for olympiad‑style problems. The model is suitable for users with access to sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS10.3 GB 11.6 GB
Too big Get file →
IQ2_M10.8 GB 12.2 GB
Too big Get file →
Q2_K_XL11.8 GB 13.1 GB
Too big Get file →
IQ3_XXS12.9 GB 14.2 GB
Too big Get file →
Q3_K_XL13.8 GB 15.1 GB
Too big Get file →
Q3_K_M14.7 GB 16.0 GB
Too big Get file →
IQ4_XS16.4 GB 17.7 GB
Too big Get file →
IQ4_NL17.3 GB 18.6 GB
Too big Get file →
Q4_K_XL17.7 GB 19.0 GB
Too big Get file →
Q4_K_M18.6 GB 19.9 GB
Too big Get file →
Q5_K_M21.7 GB 23.0 GB
Too big Get file →
Q5_K_XL21.8 GB 23.1 GB
Too big Get file →
Q6_K25.1 GB 26.4 GB
Too big Get file →
Q6_K_XL26.3 GB 27.6 GB
Too big Get file →
Q8_032.5 GB 33.8 GB
Too big Get file →
Q8_K_XL36.0 GB 37.3 GB
Too big Get file →
BF1661.1 GB 62.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (10.34 GB file, 11.6 GB memory at 8k context). For 12 GB VRAM, IQ2_M (10.85 GB file, 12.2 GB memory). For 20 GB VRAM, Q4_K_M (18.56 GB file, 19.9 GB memory).

What GPU do you need for SU 01?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (10.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.7 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_XL (21.8 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_XL (26.3 GB file, about 27.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (36.0 GB file, about 37.3 GB in use).

Which SU 01 quant should you choose?

Q4_K_M is the usual starting point for SU 01: it balances file size and quality well. Here it is a 18.6 GB file.

The Q8_0 file is 32.5 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 IQ2_XXS at 10.3 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

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byaxi0mX
Licenseapache-2.0
Downloads (HF)659
Last updated2026-05-24

Frequently asked questions about SU 01

How much VRAM does SU 01 need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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 SU 01 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SU 01 GGUF?

It depends on the quant: IQ2_XXS is 10.3 GB, IQ2_M is 10.8 GB, Q2_K_XL is 11.8 GB, IQ3_XXS is 12.9 GB, Q3_K_XL is 13.8 GB, Q3_K_M is 14.7 GB and 11 more.

What context length does SU 01 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download SU 01 GGUF?

The files are on Hugging Face in the axi0mX/SU-01-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 SU 01 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 SU‑01 on 8 GB VRAM?

Use the IQ2_XXS quantization; it requires about 11.6 GB memory at 8k context, which is close to 8 GB but may need swapping.

Does SU‑01 support image inputs?

No, the model does not have vision capabilities.

Other GGUFs of SU-01

Similar models

Browse all →

More from axi0mX

All by axi0mX →

Other medium models

All medium models →