QW

Nebius

QwenGGUF by VolkerMauelUpdated 2025-12-28
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3moe
Smallest quant0.1 GB
Quick answer

Nebius needs about 20.2 GB of memory at Q4_K_M (a 18.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.1 GB to 61.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Nebius Qwen3 30B fine‑tuned for coding and tools

Nebius is a 30.5B parameter Qwen3 model fine‑tuned with rejection sampling on SWE‑rebench trajectories. It supports up to 262,144 context tokens and is released under Apache‑2.0. The model excels in coding tasks and tool integration.

Good at

  • Coding assistance
  • Tool usage
  • Long‑form context

Limits

  • No vision support
  • Requires large VRAM for higher quant
  • License allows open use

Best for

  • Automated coding agents
  • Tool‑enabled workflows
  • Long‑context reasoning

Who it’s for. Developers and researchers needing a large language model with strong coding and tool‑usage capabilities. The model is suitable for building agents that interact with external tools and handle extensive context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_S6.8 GB 8.1 GB
Too big Get file →
IQ1_M7.5 GB 8.8 GB
Too big Get file →
IQ2_XXS8.6 GB 9.9 GB
Too big Get file →
IQ2_XS9.5 GB 10.8 GB
Too big Get file →
IQ2_S9.7 GB 11.0 GB
Too big Get file →
IQ2_M10.6 GB 11.9 GB
Too big Get file →
Q2_K_S10.9 GB 12.2 GB
Too big Get file →
Q2_K11.6 GB 12.9 GB
Too big Get file →
IQ3_XXS12.3 GB 13.6 GB
Too big Get file →
IQ3_XS13.0 GB 14.3 GB
Too big Get file →
Q3_K_S13.7 GB 15.0 GB
Too big Get file →
IQ3_S13.7 GB 15.0 GB
Too big Get file →
IQ3_M13.9 GB 15.2 GB
Too big Get file →
Q3_K15.1 GB 16.4 GB
Too big Get file →
Q3_K_M15.1 GB 16.4 GB
Too big Get file →
Q3_K_L16.3 GB 17.6 GB
Too big Get file →
IQ4_XS16.7 GB 18.0 GB
Too big Get file →
MXFP4_MOE17.4 GB 18.7 GB
Too big Get file →
IQ4_NL17.7 GB 19.0 GB
Too big Get file →
Q4_K_S17.8 GB 19.1 GB
Too big Get file →
Q4_K18.9 GB 20.2 GB
Too big Get file →
Q4_K_M18.9 GB 20.2 GB
Too big Get file →
Q5_K_S21.4 GB 22.8 GB
Too big Get file →
Q5_K22.1 GB 23.4 GB
Too big Get file →
Q5_K_M22.1 GB 23.4 GB
Too big Get file →
Q6_K25.5 GB 26.8 GB
Too big Get file →
F1661.1 GB 62.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.82 GB) or IQ1_M (7.49 GB). For 12 GB VRAM, Q2_XXS (8.59 GB) or Q3_K_M (15.08 GB) are suitable. Higher precision quants like Q4_K_M (18.92 GB) or Q5_K_M (22.09 GB) require more memory but offer better quality.

What GPU do you need for Nebius?

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 the main file (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_M (10.6 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (13.9 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K (22.1 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (25.5 GB file, about 26.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (25.5 GB file, about 26.8 GB in use).

Which Nebius quant should you choose?

Q4_K_M is the usual starting point for Nebius: it balances file size and quality well. Here it is a 18.9 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byVolkerMauel
FamilyQwen
Licenseapache-2.0
Downloads (HF)706
Last updated2025-12-28

Frequently asked questions about Nebius

How much VRAM does Nebius need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 18.9 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 Nebius on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nebius GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 6.8 GB, IQ1_M is 7.5 GB, IQ2_XXS is 8.6 GB, IQ2_XS is 9.5 GB, IQ2_S is 9.7 GB and 22 more.

What context length does Nebius 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 Nebius GGUF?

The files are on Hugging Face in the VolkerMauel/nebius-SWE-rebench-openhands-Qwen3-30B-A3B-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 Nebius 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 Nebius on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantized files, which are 6.82 GB and 7.49 GB respectively.

Does Nebius support vision tasks?

No, the model does not include vision capabilities.

What license applies to Nebius?

Nebius is released under the Apache‑2.0 license.

Other GGUFs of SWE-rebench-openhands-Qwen3-30B-A3B

Similar models

Browse all →

More Qwen models

All Qwen →

Other medium models

All medium models →