Alibaba
Qwen3-Coder 480B A35B Instruct
Frontera
Qwen3-Coder 480B A35B Instruct (480B parameters) requires approximately 297.2 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 35B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 342 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run Qwen3-Coder 480B A35B Instruct on your machine.
Run
lms load Qwen3-Coder-480B-A35B-Instruct && lms server startQuick specs
About this model
- •Significant Performance: among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving results...
- •Long-context Capabilities: with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale...
- •Agentic Coding: supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para Qwen3-Coder 480B A35B Instruct
Ejecutar este modelo
Opciones de cuantización
Estimaciones de VRAM por nivel de cuantización
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 187.2 GB | Low | — |
Q3_K_S | 3 | 235.2 GB | Low | — |
NVFP4 | 4 | 268.8 GB | Medium | — |
Q4_K_M | 4 | 292.8 GB | Medium | — |
Q5_K_M | 5 | 345.6 GB | High | — |
Q6_K | 6 | 393.6 GB | High | — |
Q8_0 | 8 | 513.6 GB | Very High | — |
F16 | 16 | 984.0 GB | Maximum | — |
Quality benchmarks
Qwen3-Coder 480B A35B Instruct benchmark scores
Coding
Source: official · 2025-07-22
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Preguntas frecuentes
FAQ — Qwen3-Coder 480B A35B Instruct
Ver también