LocalClaw/LLM/Qwen3-Coder-Next
Open-weight MoE

Qwen3-Coder-Next

Catalogue summary: Qwen Team Apache 2.0 coding-agent MoE with 80B total parameters, 3B active parameters, 262K native context and official Q4_K_M GGUF files. Practical local use fits best on 64GB+ workstations with recent llama.cpp or LM Studio-compatible runtimes.

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

64 GB catalogue minimum64 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
80B (3B active, MoE)
Minimum RAM
64 GB
Model size
48.4 GB
Quantization
Q4_K_M

Can Qwen3-Coder-Next run locally?

Qwen3-Coder-Next has a catalogue minimum of 64 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use Qwen3-Coder-Next as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): Qwen/Qwen3-Coder-Next-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningagentpowerlong-contextmoetool-calling

Install path

01
Check RAM fitMinimum 64 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch Qwen3-Coder-Next in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: qwen-coder
  • Parameters: 80B (3B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 64 GB
  • Catalogue model size: 48.4 GB
  • Tags: chat, code, reasoning, agent, power, long-context, moe, tool-calling

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
  • agent
  • power
  • long-context

Capability profile

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

speed
8
quality
9
coding
10
reasoning
9

Technical notes

Developer
Alibaba Cloud (Qwen Team)
License
Apache 2.0
Context window
262,144 tokens
Architecture
Sparse MoE causal language model based on the Qwen3-Next architecture, with 80B total parameters, 3B active parameters, 512 experts and a hybrid Gated DeltaNet / Gated Attention layout. The official card lists 262,144 tokens of native context.

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.

Workstation fitMac Studio M4 Max 64GBCUDA workstation classNVIDIA GB10 / DGX SparkLarge local models64GB RAM guide

Related catalogue entries

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

Qwen 2.5 Coder (32B) 32BQwen 3 Coder (30B) 30BQwen 2.5 Coder (7B) 7BLongCat-Flash-Lite 68.5B (3-4.5B active, MoE)Kimi Linear 48B-A3B Instruct 48B (3B active, MoE)Nemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Laguna XS 2.1 33B (3B active, MoE)Agents-A1 35B (3B active, MoE)

Where to go next