How much VRAM does Qwen 3.5 122B-A10B (MoE) need?

Qwen 3.5 122B-A10B (MoE) requires approximately 0.0 GB VRAM at Q4_K_M quantization with 1K context and 10% overhead. At Q8_0 it needs ~0.0 GB, and at FP16 ~0.0 GB. Use the PCPARTGUIDE VRAM Calculator for exact requirements at any context length and overhead setting.

Can I run Qwen 3.5 122B-A10B (MoE) on a consumer GPU?

Qwen 3.5 122B-A10B (MoE) is a 122B parameter model and requires datacenter or multi-GPU setups. At Q4_K_M, it needs approximately 0.0 GB VRAM, which exceeds consumer GPU limits. It can run on H100 (80 GB) or A100 (80 GB) datacenter GPUs, or across multiple consumer GPUs with tensor parallelism.

What is Qwen 3.5 122B-A10B (MoE)'s context window?

Qwen 3.5 122B-A10B (MoE) supports a maximum context window of 262,144 tokens. The default context is 16,384 tokens. Larger contexts require proportionally more VRAM for the KV cache — use the VRAM Calculator to estimate exact requirements at your target context length.

What quantization level should I use for Qwen 3.5 122B-A10B (MoE)?

For Qwen 3.5 122B-A10B (MoE), start with Q4_K_M (~0.0 GB) if VRAM-limited. Q8_0 offers better quality at ~2× the VRAM. If you have enough VRAM, Q6_K (~1.5× Q4 VRAM) provides a good balance. For models this large, Q3_K_M may be necessary to fit on consumer hardware.

How does Qwen 3.5 122B-A10B (MoE) compare to similar models?

Qwen 3.5 122B-A10B (MoE) is a 122.0B MoE model from the Qwen family. Browse other Qwen models on the PCPARTGUIDE directory for comparable alternatives with different parameter counts and VRAM requirements. Use the Model Transparency scores to assess documentation quality and reproducibility.

QwenMoEApache 2.0

Qwen 3.5 122B-A10B (MoE)

122.0B

Parameters

10.0B

Active

256K

Max Context

MoE

Architecture

—

Released

Text

Modality

About Qwen 3.5 122B-A10B (MoE)

Qwen 3.5 122B-A10B (MoE) is a mixture-of-experts (MoE) transformer language model from the Qwen family, containing 122B parameters across 12 layers. It has 122B total parameters loaded into VRAM with 10B active per token. It supports up to 262K tokens of context with a hidden dimension of 3072 and 2 KV heads for efficient grouped-query attention (GQA). Apache 2.0. MoE: 256 experts. DeltaNet+MoE hybrid. Server/high-end workstation.

ResearchEnterprise

Technical Specifications

Total Parameters122.0B

Active Parameters10.0B per token

ArchitectureMixture of Experts

Total Experts10

Attention TypeGQA (MoE)

Hidden Dimensiond = 3,072

Transformer Layers12

Attention Heads32

KV Headsn_kv = 2

Head Dimensiond_head = 256

Activation FunctionSwiGLU

NormalizationRMSNorm

Position EmbeddingRoPE

System Requirements

Estimated VRAM at 10% overhead for different quantization methods and context sizes.

Quantization	1K ctx	195K ctx	256K ctx
Q4_K_M0.50 B/W ~97% of FP16	63.08Datacenter GPU	67.64Datacenter GPU	69.06Datacenter GPU
Q8_01.00 B/W ~100% of FP16	126.1Cluster / Multi-GPU	130.7Cluster / Multi-GPU	132.1Cluster / Multi-GPU
F162.00 B/W Reference	252.3Cluster / Multi-GPU	256.8Cluster / Multi-GPU	258.2Cluster / Multi-GPU

Use the interactive VRAM Calculator to see exactly how much memory you need at any quantization level, context length, and overhead setting.

Open VRAM Calculator Best GPU Guide VRAM Guide