Qwen3.5-122B-A10B needs about 79.6 GB of memory at Q4_K_M (a 78.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 38.7 GB (IQ1_M) to 249.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
122‑Billion‑parameter Qwen3.5 model with vision support
Qwen3.5‑122B‑A10B is a large multimodal foundation model with 122 B parameters and 10 B active experts. It supports vision and text, trained on 262 144‑token context. The model is released under Apache‑2.0 and is compatible with llama.cpp and other inference engines.
Good at
- Vision‑language tasks
- Long‑context reasoning
- Multilingual generation
Limits
- Requires high VRAM for large quants
- No native support for GPU‑only inference in some builds
- License is Apache‑2.0
Best for
- Multimodal chat applications
- Large‑scale document summarization
- AI‑powered content creation
Who it’s for. Developers and researchers needing a high‑capacity vision‑language model for inference on powerful GPUs or CPU‑based setups. The model is suitable for enterprises building advanced AI services that require extensive context and multimodal understanding.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 38.7 GB | 40.0 GB | Too big | Get file → | |
| IQ2_XXS | 40.3 GB | 41.6 GB | Too big | Get file → | |
| IQ2_M | 40.4 GB | 41.7 GB | Too big | Get file → | |
| Q2_K_XL | 42.8 GB | 44.2 GB | Too big | Get file → | |
| IQ3_XXS | 47.8 GB | 49.2 GB | Too big | Get file → | |
| IQ3_S | 52.0 GB (3 parts) | 53.3 GB | Too big | Get file → | |
| Q3_K_M | 58.2 GB (3 parts) | 59.5 GB | Too big | Get file → | |
| Q3_K_XL | 58.4 GB (3 parts) | 59.7 GB | Too big | Get file → | |
| IQ4_XS | 61.9 GB (3 parts) | 63.2 GB | Too big | Get file → | |
| IQ4_NL | 63.2 GB (3 parts) | 64.5 GB | Too big | Get file → | |
| Q4_K_S | 73.4 GB (3 parts) | 74.8 GB | Too big | Get file → | |
| MXFP4_MOE | 76.2 GB (3 parts) | 77.6 GB | Too big | Get file → | |
| Q4_K_M | 78.3 GB (3 parts) | 79.6 GB | Too big | Get file → | |
| Q4_K_XL | 78.6 GB (3 parts) | 80.0 GB | Too big | Get file → | |
| Q5_K_S | 88.3 GB (3 parts) | 89.6 GB | Too big | Get file → | |
| Q5_K_M | 93.6 GB (3 parts) | 95.0 GB | Too big | Get file → | |
| Q5_K_XL | 93.9 GB (3 parts) | 95.2 GB | Too big | Get file → | |
| Q6_K | 104.1 GB (4 parts) | 105.4 GB | Too big | Get file → | |
| Q6_K_XL | 113.9 GB (4 parts) | 115.2 GB | Too big | Get file → | |
| Q8_0 | 132.6 GB (4 parts) | 133.9 GB | Too big | Get file → | |
| Q8_K_XL | 134.9 GB (4 parts) | 136.3 GB | Too big | Get file → | |
| BF16 | 249.4 GB (5 parts) | 250.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (38.67 GB file, ~40 GB VRAM at 8K context). For 16 GB VRAM, IQ2_XXS (40.28 GB file, ~41.6 GB VRAM) or IQ2_M (40.38 GB file, ~41.7 GB VRAM). For 24 GB VRAM, Q2_K_XL (42.85 GB file, ~44.2 GB VRAM) or IQ3_XXS (47.84 GB file, ~49.2 GB VRAM).
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: the best quant that fits is Q2_K_XL (42.8 GB file, about 44.2 GB in use).
Which Qwen3.5-122B-A10B quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5-122B-A10B: it balances file size and quality well. Here it is a 78.3 GB file.
The Q8_0 file is 132.6 GB, about 1.7 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 IQ1_M at 38.7 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
Source
Frequently asked questions about Qwen3.5-122B-A10B
How much VRAM does Qwen3.5-122B-A10B need?
About 79.6 GB at Q4_K_M with an 8K context window. That is the 78.3 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 40.0 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: IQ1_M is 38.7 GB, IQ2_XXS is 40.3 GB, IQ2_M is 40.4 GB, Q2_K_XL is 42.8 GB, IQ3_XXS is 47.8 GB, IQ3_S is 52.0 GB and 16 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 3.3 GB at 32K.
Where can I download Qwen3.5-122B-A10B GGUF?
The files are on Hugging Face in the unsloth/Qwen3.5-122B-A10B-MTP-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?
Use the IQ1_M quant, which requires about 40 GB VRAM at 8K context. 8 GB VRAM is insufficient for any quant of this model.
Does the model support vision tasks?
Yes, the model includes a vision encoder and is trained for multimodal tasks.
What license applies to this model?
The model is released under the Apache‑2.0 license.