Qwen3.5 122B A10B DASHQ Q2 needs about 39.6 GB of memory at IQ2_XS (a 38.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 35.9 GB (IQ2_XXS) to 41.0 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3.5 122B A10B DASHQ Q2 – 122B parameter LLM with 10B active experts
Qwen3.5 122B A10B DASHQ Q2 is a causal language model with a vision encoder, trained on 262144 context tokens. It contains 122B total parameters and 10B active parameters in a mixture‑of‑experts architecture. The model is released under the apache‑2.0 license.
Good at
- Large‑scale text generation
- Multimodal reasoning
- High‑throughput inference
Limits
- No vision tower included in GGUF
- Large memory requirement for 8k context
- Requires recent llama.cpp build
Best for
- Enterprise content creation
- Research prototyping
- AI‑driven applications
Who it’s for. Developers and researchers needing a large, efficient LLM with expert routing. The model is suitable for teams with access to sufficient GPU memory and a recent llama.cpp environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 35.9 GB | 37.2 GB | Too big | Get file → | |
| IQ2_XS | 38.3 GB | 39.6 GB | Too big | Get file → | |
| Q2_K_XL | 41.0 GB | 42.4 GB | Too big | Get file → |
For 8GB VRAM use IQ2_XXS (file size 35.92 GB, memory 37.2 GB at 8k context). For 12GB VRAM use IQ2_XS (38.34 GB, 39.6 GB). For 16GB VRAM use Q2_K_XL (41.05 GB, 42.4 GB). Memory estimates are approximate.
What GPU do you need for Qwen3.5 122B A10B DASHQ Q2?
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 (41.0 GB file, about 42.4 GB in use).
Which Qwen3.5 122B A10B DASHQ Q2 quant should you choose?
IQ2_XS (38.3 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 35.9 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 DASHQ Q2
How much VRAM does Qwen3.5 122B A10B DASHQ Q2 need?
About 39.6 GB at IQ2_XS with an 8K context window. That is the 38.3 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 DASHQ Q2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 37.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5 122B A10B DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 35.9 GB, IQ2_XS is 38.3 GB, Q2_K_XL is 41.0 GB.
What context length does Qwen3.5 122B A10B DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/Qwen3.5-122B-A10B-DASHQ-Q2-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 DASHQ Q2 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 8GB VRAM?
With the IQ2_XXS quantization the model requires about 37.2 GB of VRAM at 8k context, so 8GB is insufficient.
Does the GGUF file include vision capabilities?
No, the GGUF files contain only the text model; the vision tower is not included.
What license applies to this model?
The model is released under the apache‑2.0 license, inherited from the base model.