qwen3-coder

Alibaba's performant long context models for agentic and coding tasks.

Araç Kullanımı 30b 480b

Hızlı Kurulum (Ollama kuruluysa)

ollama run qwen3-coder

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

Etiket	Boyut	Bağlam	Girdi	Komut
latest	19GB	256K	Text	`ollama run qwen3-coder:latest`
30b	19GB	256K	Text	`ollama run qwen3-coder:30b`
480b	290GB	256K	Text	`ollama run qwen3-coder:480b`
30b-a3b-q4_K_M	19GB	256K	Text	`ollama run qwen3-coder:30b-a3b-q4_K_M`
30b-a3b-q8_0	32GB	256K	Text	`ollama run qwen3-coder:30b-a3b-q8_0`
30b-a3b-fp16	61GB	256K	Text	`ollama run qwen3-coder:30b-a3b-fp16`
480b-a35b-q4_K_M	290GB	256K	Text	`ollama run qwen3-coder:480b-a35b-q4_K_M`
480b-a35b-q8_0	510GB	256K	Text	`ollama run qwen3-coder:480b-a35b-q8_0`
480b-a35b-fp16	960GB	256K	Text	`ollama run qwen3-coder:480b-a35b-fp16`

Model Detayları ve Benchmarklar (kaynak: ollama.com)

Qwen 3 logo Qwen3-Coder is the most agentic code model to date in the Qwen series.

480B

Cloud

ollama run qwen3-coder:480b-cloud

Local

ollama run qwen3-coder:480b

Running locally requires a minimum of 250GB of memory or unified memory.

30B

ollama run qwen3-coder:30b

qwen3-coder:30b offers 30B total parameters with only 3.3B activated, delivering strong performance while maintaining efficiency.

Exceptional agentic capabilities for real-world software engineering tasks through advanced long-horizon reinforcement learning on SWE-Bench and similar benchmarks.
Long context support with 256K tokens natively and up to 1M tokens using extrapolation methods, optimized for repository-scale understanding.
Scaled pretraining on 7.5T tokens (70% code ratio) while preserving strong general and mathematical abilities.
Execution-driven reinforcement learning that significantly boosts code execution success rates across diverse real-world coding tasks.