List of large language models

Apr 20, 2026 - 16:52
0 0
List of large language models

2026: Add Qwen3.6 (Qwen3.6-35B-A3B)

← Previous revision Revision as of 11:21, 20 April 2026
Line 1,037: Line 1,037:
| {{yes|[[MIT License|MIT]]}}
| {{yes|[[MIT License|MIT]]}}
| MoE model designed for agentic coding{{cite web |last1=Franzen |first1=Carl |title=AI joins the 8-hour work day as GLM ships 5.1 open source LLM, beating Opus 4.6 and GPT-5.4 on SWE-Bench Pro |url=https://venturebeat.com/technology/ai-joins-the-8-hour-work-day-as-glm-ships-5-1-open-source-llm-beating-opus-4 |website=[[VentureBeat]] |access-date=12 April 2026 |date=7 April 2026}}{{Cite web |title=GLM-5.1: Towards Long-Horizon Tasks |url=https://z.ai/blog/glm-5.1 |access-date=12 April 2026 |website=Z.ai |language=en}}
| MoE model designed for agentic coding{{cite web |last1=Franzen |first1=Carl |title=AI joins the 8-hour work day as GLM ships 5.1 open source LLM, beating Opus 4.6 and GPT-5.4 on SWE-Bench Pro |url=https://venturebeat.com/technology/ai-joins-the-8-hour-work-day-as-glm-ships-5-1-open-source-llm-beating-opus-4 |website=[[VentureBeat]] |access-date=12 April 2026 |date=7 April 2026}}{{Cite web |title=GLM-5.1: Towards Long-Horizon Tasks |url=https://z.ai/blog/glm-5.1 |access-date=12 April 2026 |website=Z.ai |language=en}}
|-
| Qwen3.6 (Qwen3.6-35B-A3B)
| {{dts|2026-04-15|format=md|abbr=on}}
| [[Alibaba Cloud]]
| 35
| {{Unknown}}
| {{Unknown}}
| {{yes|[[Apache 2.0]]}}
| MoE model with 3B active parameters out of 35B total{{cite web |title=A Chinese AI called 'Qwen3.6-35B-A3B,' which is more powerful than Gemma4, has been released as an open model. |url=https://gigazine.net/gsc_news/en/20260417-qwen36-35b-a3b |website={{ill|Gigazine|jp}} |access-date=17 April 2026 |date=17 April 2026}}{{cite web |title=README.md · Qwen/Qwen3.6-35B-A3B |url=https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/README.md |via=[[Hugging Face]] |access-date=17 April 2026 |date=15 April 2026}}
|}
|}


Read More