Alibaba
Qwen 3.5 122B A10B (122B parameters) requires approximately 78.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 10B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 91 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Qwen 3.5 122B A10B on your machine.
Run
lms load Qwen3.5-122B-A10B-Instruct && lms server startQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | — |
Q3_K_S | 3 | 59.8 GB | Low | — |
NVFP4 | 4 | 68.3 GB | Medium | — |
Q4_K_M | 4 | 74.4 GB | Medium | — |
Q5_K_M | 5 | 87.8 GB | High | — |
Q6_K | 6 | 100.0 GB | High | — |
Q8_0 | 8 | 130.5 GB | Very High | — |
F16 | 16 | 250.1 GB | Maximum | — |
Quality benchmarks
Coding
Reasoning
General
Source: official · 2025-06-25
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Qwen 3.5 122B A10B (122B parameters) requires approximately 78.4 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac Studio M3 Ultra 256GB can run Qwen 3.5 122B A10B with a compatibility score of 93/100. It provides 256 GB of memory and achieves approximately 34.7 tokens per second.
The recommended quantization for Qwen 3.5 122B A10B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Qwen 3.5 122B A10B: AMD Instinct MI250X 128GB (score: 99/100), AMD Instinct MI300A 128GB (score: 99/100), Gaudi 3 128GB (score: 99/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Qwen 3.5 122B A10B is well-suited for chat as well as coding, reasoning, rag. It was designed with these use cases in mind.
See also
