CanItRun Logocanitrun.

Qwen 3.5 122B-A10B (MoE)

Qwen 3.5 122B-A10B (MoE) needs roughly 79.3 GB VRAM at Q4_K_M quantization (275.7 GB at FP16). 29 GPUs we track can run it fully in VRAM at 8k context.

29 GPUs run this natively · 17 with CPU offload

Alibaba122B params10B active (MoE)256k contextApache 2.0Commercial use ok

Qwen 3.5 122B-A10B (MoE) is a Mixture of Experts (MoE) large language model with 122B total parameters but only 10B active per token developed by Alibaba. Released in February 2026, it supports text and vision inputs with a 128K context window, released under the Apache 2.0 license, allowing commercial use.

To run Qwen 3.5 122B-A10B (MoE) locally, you need approximately 79.3 GB of VRAM at Q4_K_M quantization with 8k context. 29 of the GPUs we track can run it fully in VRAM, with a further 17 able to offload to system RAM. At Q4_K_M it requires 79.3 GB — more than any single consumer GPU. A multi-GPU server or 80 GB datacenter GPU is required. At Q8_K_M (139.0 GB), you get near-FP16 quality while still fitting on large server or multi-GPU setups. FP16 requires 275.7 GB, limiting it to datacenter-class hardware with 80 GB+ VRAM. As a MoE model, inference speed depends on active parameters (10B) rather than total size, so once it fits in VRAM it runs noticeably faster than dense models of the same parameter count.

Its MMLU-Pro score of 86.7 places it among the strongest open-weight models available. The license allows commercial use.

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP32488.0 GB2.15 GB549.0 GB
BF16244.0 GB2.15 GB275.7 GB
FP16244.0 GB2.15 GB275.7 GB
Q8_0122.0 GB2.15 GB139.1 GB
Q6_K100.0 GB2.15 GB114.5 GB
Q5_K_M78.6 GB2.15 GB90.4 GB
Q4_K_M68.7 GB2.15 GB79.3 GB
Q3_K_Mrec52.5 GB2.15 GB61.2 GB
Q2_K40.1 GB2.15 GB47.4 GB
NVFP4cuda61.0 GB2.15 GB70.7 GB

KV cache shown at 8k context (FP16). NVFP4 requires a CUDA GPU. Enable TurboQuant in the calculator to see reduced KV cache estimates.

Benchmarks

MMLU-Pro
86.7

GPUs that run Qwen 3.5 122B-A10B (MoE) natively (29)

Plus 17 GPUs that run it with CPU offload (slower)
Hugging Face ↗Ollama ↗Released 2026-02-15

Frequently asked questions

What are the VRAM requirements for Qwen 3.5 122B-A10B (MoE)?
Qwen 3.5 122B-A10B (MoE) requires approximately 79.3 GB of VRAM at Q4_K_M quantization, 139.0 GB at Q8, and 275.7 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Qwen 3.5 122B-A10B (MoE) have?
Qwen 3.5 122B-A10B (MoE) has 122 billion total parameters, but only 10 billion are active per token thanks to its Mixture of Experts (MoE) architecture. This makes inference significantly faster than the total parameter count suggests.
How capable is Qwen 3.5 122B-A10B (MoE)?
Qwen 3.5 122B-A10B (MoE) achieves an MMLU-Pro score of 86.7, placing it among the most capable open-weight models available — competitive with frontier systems on general knowledge and reasoning.
Can Qwen 3.5 122B-A10B (MoE) run on a 16 GB GPU?
No. At Q4_K_M, Qwen 3.5 122B-A10B (MoE) needs 79.3 GB of VRAM — more than 16 GB. You will need a multi-GPU server.
Can Qwen 3.5 122B-A10B (MoE) run on a 24 GB GPU?
No. Even at Q4_K_M, Qwen 3.5 122B-A10B (MoE) needs 79.3 GB. Consider a multi-GPU server with 80 GB+ total VRAM.
What is the smallest quantization for Qwen 3.5 122B-A10B (MoE) that fits in 24 GB of VRAM?
Qwen 3.5 122B-A10B (MoE) cannot fit in 24 GB of VRAM at any standard quantization level. The minimum needed is 47.4 GB at Q2_K.
What GPU do I need to run Qwen 3.5 122B-A10B (MoE) locally?
You need a multi-GPU server. At Q4_K_M, Qwen 3.5 122B-A10B (MoE) needs 79.3 GB VRAM, more than any single consumer GPU. Consider 2–4× H100 or A100 GPUs.