Qwen3.5-122B-A10B needs about 76.7 GB of memory at Q4_K_M (a 75.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.4 GB to 244.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3.5-122B-A10B, a 122B parameter Mixture of Experts model
Qwen3.5-122B-A10B is a 122B parameter model with 10B active parameters in its MoE architecture. It supports reasoning, tools, and vision tasks and was quantized with llama.cpp. The model is released under the apache-2.0 license.
Good at
- Reasoning and complex problem solving
- Multimodal vision-language tasks
- Tool use and agentic behavior
Limits
- Requires high VRAM for full precision
- Large context length demands significant memory
- No explicit vision support in all quantizations
Best for
- Enterprise AI assistants
- Multimodal content generation
- Research on MoE architectures
Who it’s for. Developers and researchers needing a large, multimodal LLM with Mixture of Experts capability. The model is suitable for environments with sufficient GPU memory and a need for advanced reasoning and vision tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 37.8 GB | 39.1 GB | Too big | Get file → | |
| IQ1_M | 43.3 GB | 44.6 GB | Too big | Get file → | |
| Q2_K_M | 46.8 GB | 48.1 GB | Too big | Get file → | |
| IQ2_S | 49.0 GB | 50.3 GB | Too big | Get file → | |
| IQ2_M | 51.1 GB | 52.4 GB | Too big | Get file → | |
| IQ3_XXS | 57.6 GB (2 parts) | 58.9 GB | Too big | Get file → | |
| IQ3_XS | 57.9 GB (2 parts) | 59.2 GB | Too big | Get file → | |
| Q3_K_M | 60.9 GB (2 parts) | 62.2 GB | Too big | Get file → | |
| IQ3_M | 62.4 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| IQ3_S | 62.4 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| IQ4_XS | 65.3 GB (2 parts) | 66.6 GB | Too big | Get file → | |
| Q4_0 | 68.8 GB (2 parts) | 70.1 GB | Too big | Get file → | |
| Q4_K_M | 75.4 GB (2 parts) | 76.7 GB | Too big | Get file → | |
| Q4_1 | 76.5 GB (2 parts) | 77.8 GB | Too big | Get file → | |
| Q5_0 | 84.1 GB (2 parts) | 85.4 GB | Too big | Get file → | |
| Q5_K_M | 89.3 GB (2 parts) | 90.6 GB | Too big | Get file → | |
| Q5_1 | 91.7 GB (2 parts) | 93.0 GB | Too big | Get file → | |
| Q6_K_M | 100.4 GB (3 parts) | 101.7 GB | Too big | Get file → | |
| Q8_0 | 129.9 GB (3 parts) | 131.2 GB | Too big | Get file → | |
| BF16 | 219.7 GB (5 parts) | 221.0 GB | Too big | Get file → | |
| F16 | 219.7 GB (5 parts) | 221.0 GB | Too big | Get file → | |
| F16 | 244.3 GB (6 parts) | 245.6 GB | Too big | Get file → |
For 8‑16 GB VRAM, use Q4_0 or Q4_K_M (file size 68.84 GB, 70.1 GB memory). For 16‑32 GB VRAM, Q5_0 or Q5_K_M (84.1 GB, 85.4 GB memory) are appropriate. For 32‑64 GB VRAM, Q6_K_M (100.35 GB, 101.7 GB memory) or Q8_0 (129.87 GB, 131.2 GB memory) provide higher quality.
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: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 48 GB VRAM: the best quant that fits is IQ1_M (43.3 GB file, about 44.6 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 75.4 GB file.
The Q8_0 file is 129.9 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 the first one in the table at 0.4 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
Source
Frequently asked questions about Qwen3.5-122B-A10B
How much VRAM does Qwen3.5-122B-A10B need?
About 76.7 GB at Q4_K_M with an 8K context window. That is the 75.4 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?
Yes, with the smaller files: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5-122B-A10B GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 37.8 GB, IQ1_M is 43.3 GB, Q2_K_M is 46.8 GB, IQ2_S is 49.0 GB, IQ2_M is 51.1 GB and 17 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 Mungert/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 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 quantization requires at least 70.1 GB memory at 8k context.
Does the model support vision tasks?
Yes, the model has vision capabilities as listed in its detected abilities.
What license applies to this model?
The model is released under the apache-2.0 license.