QW

Qwen3.5-122B-A10B

QwenGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant48.3 GB
Quick answer

Qwen3.5-122B-A10B needs about 79.0 GB of memory at its main file (a 77.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 48.3 GB to 89.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3.5-122B-A10B – 122B parameter multimodal LLM with MoE

Qwen3.5-122B-A10B is a causal language model with vision encoder, built on the qwen35moe architecture. It contains 122B total parameters, with 10B active in the mixture‑of‑experts. The model supports 201 languages and multimodal tasks.

Good at

  • Vision‑language reasoning
  • Large‑scale multimodal inference
  • High‑throughput MoE inference

Limits

  • Requires large VRAM for full model
  • No explicit vision‑only mode
  • License is apache‑2.0

Best for

  • Multimodal chat applications
  • Vision‑enabled content generation
  • Large‑scale inference on high‑memory GPUs

Who it’s for. Developers and enterprises needing a unified vision‑language foundation model with efficient MoE architecture. Suitable for teams with access to GPUs with 122 GB unified memory or larger.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—48.3 GB 49.6 GB
Too big Get file →
—59.2 GB 60.5 GB
Too big Get file →
—59.2 GB 60.5 GB
Too big Get file →
—77.7 GB 79.0 GB
Too big Get file →
—77.7 GB 79.0 GB
Too big Get file →
—89.6 GB 90.9 GB
Too big Get file →
—89.6 GB 90.9 GB
Too big Get file →

The base GGUF files range from 48.3 GB to 89.62 GB. For 8 GB VRAM, the smallest 48.3 GB file will still exceed memory; a higher‑compression quant (not listed) would be required. For 16 GB VRAM, the 59.21 GB file is still too large. The 77.65 GB and 89.62 GB files are suitable only on GPUs with 122 GB unified memory or larger.

What GPU do you need for Qwen3.5-122B-A10B?

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.

Which Qwen3.5-122B-A10B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 48.3 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

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

Source

Quantized bymudler
FamilyQwen
Licenseapache-2.0
Downloads (HF)3,688
Last updated2026-08-17

Frequently asked questions about Qwen3.5-122B-A10B

How much VRAM does Qwen3.5-122B-A10B need?

About 79.0 GB at its main file with an 8K context window. That is the 77.7 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5-122B-A10B GGUF?

It depends on the quant: file is 48.3 GB, file is 59.2 GB, file is 59.2 GB, file is 77.7 GB, file is 77.7 GB, file is 89.6 GB and 1 more.

What context length does Qwen3.5-122B-A10B 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 GGUF?

The files are on Hugging Face in the mudler/Qwen3.5-122B-A10B-APEX-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 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 Qwen3.5-122B-A10B on 8 GB VRAM?

No. The smallest GGUF file is 48.3 GB, which exceeds 8 GB VRAM. A higher‑compression quant would be needed.

What is the context length of this model?

The model was trained on 262144 tokens and can handle up to that context length.

Does this model support vision tasks?

Yes. It includes a vision encoder and supports vision‑language tasks.

Other GGUFs of Qwen3.5-122B-A10B

Similar models

Browse all →

More from mudler

All by mudler →

More Qwen models

All Qwen →

Other large models

All large models →