LocalClaw/LLM/Qwen 3.5 MoE (122B/10B active)
Open-weight local LLM

Qwen 3.5 MoE (122B/10B active)

Catalogue summary: Large MoE model with only 10B active params. 60% cheaper to run than Qwen3-Max. 256K context. Top-tier reasoning, coding and multilingual. Hybrid think/non-think. Apache 2.0.

Repository editorial metadata; verify comparative claims in the linked upstream material.

80 GB catalogue minimum80 GB RAMQ4_K_MCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
122B (10B active)
Minimum RAM
80 GB
Model size
65 GB
Quantization
Q4_K_M

Can Qwen 3.5 MoE (122B/10B active) run locally?

Qwen 3.5 MoE (122B/10B active) has a catalogue minimum of 80 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use qwen3.5-122b-a10b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Public GGUF repository (verified 2026-09-07): lmstudio-community/Qwen3.5-122B-A10B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningqualitypower

Install path

01
Check RAM fitMinimum 80 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch qwen3.5-122b-a10b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: qwen
  • Parameters: 122B (10B active)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 80 GB
  • Catalogue model size: 65 GB
  • Tags: chat, code, reasoning, quality, power

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • quality
  • power

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
4
quality
10
coding
9
reasoning
10

Technical notes

Developer
Alibaba Cloud (Qwen Team)
License
Apache 2.0
Context window
262,144 tokens
Architecture
Mixture of Experts (MoE) — 122B total, 10B active per token. Large-scale sparse MoE with hybrid attention.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Qwen 3 (32B) 32BQwen 3.6 (27B) 27BQwen 3.5 (27B) 27BQwen 3.6 35B-A3B 35B (3B active, MoE)Qwen AgentWorld 35B-A3B 35B (3B active, MoE)Qwen3.8-27B 27BQwen 2.5 (72B) 72BQwen 3.5 MoE (35B/3B active) 35B (3B active)

Where to go next