Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is an open-weights language model from Qwen, released February 23, 2026. It has 125B parameters (mixture-of-experts, 10B active). The context window is 256K tokens. API price: $0.4 input / $3.2 output per million tokens.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to …
Check it against your own PC →
Can you run Qwen3.5 122B-A10B locally?
The smallest common GPU it runs on is 12 GB of VRAM (with 32 GB of RAM): IQ2_XXS, GPU + experts in RAM, roughly 32 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Runs · GPU + CPU experts | IQ2_XXS (heavy loss) | 11.2 GB | 22.0 GB | ~32 |
| 16 GB VRAM | Runs · GPU + CPU experts | IQ2_XXS (heavy loss) | 15.2 GB | 18.0 GB | ~39 |
| 24 GB VRAM | Runs · GPU + CPU experts | IQ3_XXS (noticeable loss) | 23.2 GB | 25.6 GB | ~33 |
| 32 GB VRAM | Runs · GPU + CPU experts | IQ3_XXS (noticeable loss) | 31.2 GB | 17.6 GB | ~47 |
Ready-made quantizations on Hugging Face: HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive · unsloth/Qwen3.5-122B-A10B-GGUF · mradermacher/Qwen3.5-122B-A10B-GGUF · bartowski/Qwen_Qwen3.5-122B-A10B-GGUF · unsloth/Qwen3.5-122B-A10B-MTP-GGUF · lmstudio-community/Qwen3.5-122B-A10B-GGUF
Benchmark results
Epoch AI has not published results for Qwen3.5 122B-A10B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: Qwen/Qwen3.5-122B-A10B
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash