Qwen 3.5 122B-A10B (MoE) — VRAM Requirements
Written by Jakub Rusinowski · Last updated July 21, 2026
How much GPU VRAM you need to run Qwen 3.5 (Legacy Listing — Unverified) Qwen 3.5 122B-A10B (MoE) by Alibaba Cloud locally, a 122B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Qwen 3.5 122B-A10B (MoE) needs about 74 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 40.1 GB | 40.9 GB |
| Q3_K_M | 3.41 | 52.0 GB | 52.8 GB |
| Q4_K_M | 4.83 | 73.7 GB | 74.5 GB |
| Q5_K_M | 5.67 | 86.5 GB | 87.3 GB |
| Q6_K | 6.56 | 100.0 GB | 100.8 GB |
| Q8_0 | 8.50 | 129.6 GB | 130.4 GB |
| F16 | 16.00 | 244.0 GB | 244.8 GB |
Switch quantization in the interactive calculator, or see the full Qwen 3.5 (Legacy Listing — Unverified) model page.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/qwen3-5-legacy-122b-a10b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.