qwen2.5

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Ollama
• Developer / product site

From Alibaba Cloud Qwen

Models in the qwen2.5 line

• qwen2.5:0.5b
• qwen2.5:0.5b-128k
• qwen2.5:0.5b-64k
• qwen2.5:1.5b
• qwen2.5:14b
• qwen2.5:32b
• qwen2.5:3b
• qwen2.5:7b

Named in 9 observation pages

• 14B-32B local models — all 47 · V1
• 3B-7B local models — all 53 · V1
• A consumer GPU recorded higher throughput than a 48-core Xeon · V1
• How models scale under concurrent slots · V1
• NVIDIA GTX 1070 — 344 models profiled · V1
• Sub-3B local models — all 34 · V1
• The capability ladder — execution-verified · V1
• The minimum viable model probe · V1
• Xeon vs AMD workstation — CPU inference head-to-head · V1