QW

Qwen3.5 122B A10B Uncensored APEX Compact

QwenGGUF by SC117Updated 2026-10-03
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant59.2 GB
Quick answer

Qwen3.5 122B A10B Uncensored APEX Compact needs about 60.5 GB of memory at its main file (a 59.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3.5 122B A10B Uncensored APEX Compact – large multimodal MoE model

Qwen3.5 122B A10B Uncensored APEX Compact is a 122B parameter, 10B active MoE model with 262,144 native context tokens. It supports text, image, and video input and is released under the apache-2.0 license.

Good at

  • Multimodal inference
  • Large context handling
  • Uncensored text generation

Limits

  • Requires 60.5 GB VRAM at 8k context
  • No specialized runtime needed
  • Vision requires mmproj file

Best for

  • Research on multimodal LLMs
  • Large context document summarization
  • Uncensored content creation

Who it’s for. Researchers and developers needing a large, multimodal LLM with uncensored behavior and a 262K token context window. The model is suitable for advanced inference tasks where high parameter count and MoE efficiency are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—59.2 GB 60.5 GB
Too big Get file →

The only available quant is the unknown quant with a file size of 59.21 GB. It requires approximately 60.5 GB VRAM at 8k context. For lower memory budgets, no other quant is listed, so this model is not recommended for systems with less than 60 GB VRAM.

What GPU do you need for Qwen3.5 122B A10B Uncensored APEX Compact?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters122B (approximate, mixture of experts)
Active parameters10B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bySC117
FamilyQwen
Licenseapache-2.0
Downloads (HF)697
Last updated2026-10-03

Frequently asked questions about Qwen3.5 122B A10B Uncensored APEX Compact

How much VRAM does Qwen3.5 122B A10B Uncensored APEX Compact need?

About 60.5 GB at its main file with an 8K context window. That is the 59.2 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 Qwen3.5 122B A10B Uncensored APEX Compact on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 60.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 122B A10B Uncensored APEX Compact GGUF?

It depends on the quant: file is 59.2 GB.

What context length does Qwen3.5 122B A10B Uncensored APEX Compact 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 Qwen3.5 122B A10B Uncensored APEX Compact GGUF?

The files are on Hugging Face in the SC117/Qwen3.5-122B-A10B-Uncensored-APEX-Compact-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 Qwen3.5 122B A10B Uncensored APEX Compact 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 this model on 8 GB VRAM?

No. The model requires about 60.5 GB VRAM at 8k context, far exceeding 8 GB.

Does the model support vision tasks?

Yes, it is natively multimodal and supports text, image, and video input.

What license does the model use?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

Similar models

Browse all →

More from SC117

All by SC117 →

More Qwen models

All Qwen →

Other large models

All large models →