Qwen Coder Next is an 80B MoE with 3B active parameters designed for coding agents and local development. Excels at long-horizon reasoning, complex tool usage, and recovery from execution failures.

Stats

2 Downloads

Capabilities

Trained for tool use

Minimum system memory

42GB

qwen3-coder-next

Public

Forked from qwen/qwen3-coder-next

Model

Revisions

README

Parameters

Custom configuration options included with this model

Temperature

Top K Sampling

Top P Sampling

0.95

Sources

The underlying model files this model uses

Based on

🤗lmstudio-community/Qwen3-Coder-Next-GGUF→

GGUF

🤗lmstudio-community/Qwen3-Coder-Next-MLX-4bit→

MLX

Qwen3 Coder Next

Qwen3 Coder Next is an 80B MoE with 3B active parameters designed for coding agents and local development.

Excels at long-horizon reasoning, complex tool usage, and recovery from execution failures.

🤗lmstudio-community/Qwen3-Coder-Next-MLX-6bit→

MLX

🤗lmstudio-community/Qwen3-Coder-Next-MLX-8bit→

MLX