Alibaba
Qwen 3.6 Plus (110B)
Strong all-round model with high reasoning performance
Model Summary
Family
Qwen
Version
3.6
Parameters
110B (est.)
Parameter counts for closed models are estimates; vendors rarely publish exact sizes.
VRAM Requirements by Quantization
Memory needed to serve Qwen 3.6 Plus (110B) for inference, including a 20% overhead for activations and KV cache.
| Precision | VRAM needed | Smallest single GPU that fits |
|---|---|---|
| INT4 (4-bit) | 61.47 GB | NVIDIA H100 SXM5 (80 GB) |
| INT8 (8-bit) | 122.93 GB | NVIDIA H200 SXM5 (141 GB) |
| FP16 (16-bit) | 245.87 GB | AMD Instinct MI325X (256 GB) |
| FP32 (32-bit) | 491.74 GB | Multi-GPU required |
Recommended GPU Configurations
Cheapest on-demand configurations to serve Qwen 3.6 Plus (110B) at 8-bit (123 GB VRAM).
1x AMD Instinct MI300X
192 GB total VRAM · CDNA 3
~$6.00/h
1x AMD Instinct MI325X
256 GB total VRAM · CDNA 3
~$8.00/h
2x NVIDIA A100 80GB
160 GB total VRAM · Ampere
~$9.00/h
Quick GPU Planning
Use the calculator pre-filled with this exact version to estimate memory, speed, and compute requirements in a few clicks.
Access Pre-filled CalculatorFrequently Asked Questions
How much VRAM do you need to run Qwen 3.6 Plus (110B)?
With an estimated 110B parameters, Qwen 3.6 Plus (110B) needs roughly 123 GB of VRAM in 8-bit (INT8), 61 GB in 4-bit, and 246 GB in FP16, including a 20% overhead for activations and KV cache.
Which GPUs can run Qwen 3.6 Plus (110B)?
At 8-bit quantization, the most cost-effective option is 1x AMD Instinct MI300X (192 GB combined VRAM, around $6.00/hour on-demand). Higher-end cards like the NVIDIA B200 or AMD MI355X reduce the GPU count needed.
Can Qwen 3.6 Plus (110B) run on a single GPU?
Yes. In 8-bit, a single NVIDIA H200 SXM5 (141 GB) fits the model.
How much does it cost to serve Qwen 3.6 Plus (110B) in the cloud?
Renting 1x Instinct MI300X costs on the order of $6.00/hour, i.e. about $4,380/month running 24/7. Actual prices vary by provider and commitment; spot and reserved capacity can be significantly cheaper.
Deploy on a GPU cloud
Rent 1x Instinct MI300X by the hour instead of buying hardware.
