QW

Qwen_Qwen3.5 122B A10B

QwenGGUF by lmstudio-communityUpdated 2026-02-24
Download on Hugging Face
Parameters122B
Context256K
Layers48
Architectureqwen35moe
Smallest quant74.2 GB
Quick answer

Qwen_Qwen3.5 122B A10B needs about 75.5 GB of memory at Q4_K_M (a 74.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 74.2 GB (Q4_K_M) to 129.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3.5 122B A10B – 122B parameter multimodal model

Qwen3.5 122B A10B is a 122‑billion‑parameter causal language model with vision encoder. It uses a gated DeltaNet and sparse Mixture‑of‑Experts architecture, enabling efficient inference. The model supports 201 languages and 262,144‑token context.

Good at

  • Vision‑language tasks
  • Large‑context reasoning
  • Multilingual generation

Limits

  • Requires >75 GB VRAM for Q4_K_M at 8 k context
  • No text‑only quantization available
  • License is Apache‑2.0

Best for

  • Multimodal chatbots
  • Image‑guided code generation
  • Large‑scale document summarization

Who it’s for. Developers and researchers needing a high‑capacity vision‑language model. The model is suitable for applications that can accommodate the large VRAM requirement and benefit from multimodal capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M74.2 GB (2 parts) 75.5 GB
Too big Get file →
Q6_K100.3 GB (3 parts) 101.6 GB
Too big Get file →
Q8_0129.9 GB (4 parts) 131.2 GB
Too big Get file →

For 8 GB VRAM, the Q4_K_M quant is the smallest, but still needs ~75 GB VRAM at 8 k context. With 16 GB VRAM, Q6_K is still too large. The model is best run on systems with 75 GB or more VRAM using Q4_K_M. For higher memory budgets, Q6_K or Q8_0 can be used, but memory usage increases proportionally.

What GPU do you need for Qwen_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 Qwen_Qwen3.5 122B A10B quant should you choose?

Q4_K_M is the usual starting point for Qwen_Qwen3.5 122B A10B: it balances file size and quality well. Here it is a 74.2 GB file.

The Q8_0 file is 129.9 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.

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 bylmstudio-community
FamilyQwen
Licenseapache-2.0
Downloads (HF)5,816
Last updated2026-02-24

Frequently asked questions about Qwen_Qwen3.5 122B A10B

How much VRAM does Qwen_Qwen3.5 122B A10B need?

About 75.5 GB at Q4_K_M with an 8K context window. That is the 74.2 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 Qwen_Qwen3.5 122B A10B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 75.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen_Qwen3.5 122B A10B GGUF?

It depends on the quant: Q4_K_M is 74.2 GB, Q6_K is 100.3 GB, Q8_0 is 129.9 GB.

What context length does Qwen_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 Qwen_Qwen3.5 122B A10B GGUF?

The files are on Hugging Face in the lmstudio-community/Qwen3.5-122B-A10B-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 Qwen_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 quant requires about 75 GB VRAM at 8 k context, far exceeding 8 GB.

Does the model support text‑only inference?

Yes, but the quantized GGUF files are provided for vision‑language use; text‑only inference is possible with the same weights.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-122B-A10B

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Qwen models

All Qwen →

Other large models

All large models →