How much VRAM does Qwen3.5 122B A10B need?

Qwen3.5 122B A10B (122B parameters) requires approximately 92.8 GB of memory with Q3_K_M quantization.

What is the best quantization for Qwen3.5 122B A10B?

The recommended quantization for Qwen3.5 122B A10B is Q3_K_M, which balances quality and memory efficiency.

Can it run?

Yes, Gaudi 3 128GB can run Qwen3.5 122B A10B with a C grade (Runs well). Expected decode speed: 40.3 tok/s.

CUsable

Runs well

Using Q3_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

40.3 tok/s

TTFT

4805 ms

Safe context

22K

Memory

92.8 GB / 128.0 GB

Weights59.8 GB

KV Cache19.1 GB

Runtime1.2 GB

Headroom12.8 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Tight fit	40.3 tok/s	6989 ms	37K
Chat	C	Runs well	40.3 tok/s	2621 ms	12K
Coding	C	Runs well	40.3 tok/s	4805 ms	22K
RAG	C	Tight fit	40.3 tok/s	8736 ms	37K
Reasoning	C	Runs well	40.3 tok/s	5678 ms	22K

How Qwen3.5 122B A10B (122B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	D37
Q3_K_S	3	59.8 GB	Low	D40
NVFP4	4

HuggingFace

huggingface-cli download hf-unsloth--qwen3-5-122b-a10b-gguf

Upgrade options

NVIDIA H200 141GBBudget pick

B62.7 tok/s decode

~$30,000 MSRP

NVIDIA H200 PCIe 141GBBest value

B62.7 tok/s decode

~$30,000 MSRP