{"schema_version":"onlylabs.public_signal.v1","title":"Qwen (Alibaba Cloud) Writing: Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","description":"Qwen (Alibaba Cloud) writing signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4","json_url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","generated_at":"2026-06-07T21:16:32.787981+00:00","org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/qwen","dossier_json_url":"https://onlylabs.fyi/labs/qwen/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4","signal_json":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","source":"https://qwenlm.github.io/blog/qwen-moe/","lab_dossier":"https://onlylabs.fyi/labs/qwen","lab_dossier_json":"https://onlylabs.fyi/labs/qwen/dossier.json","analysis":"https://onlylabs.fyi/analysis/qwen","analysis_json":"https://onlylabs.fyi/analysis/qwen/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/qwen/evidence.json","category":"https://onlylabs.fyi/frontier","category_json":"https://onlylabs.fyi/frontier.json","category_feed":"https://onlylabs.fyi/frontier/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","topic":"https://onlylabs.fyi/topics/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml","data_business":null},"answer_pack":{"answer":"Qwen (Alibaba Cloud) published Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Community criticizes misleading naming and high VRAM usage despite fewer active parameters. · Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters | Qwen We have a new blog! View this page at qwen.ai . This page will automatically redirect in.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","signal_desk":"talking","source_context":{"source_url":"https://qwenlm.github.io/blog/qwen-moe/","source_host":"qwenlm.github.io","occurred_at":"2024-03-28T03:31:44+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date","context":null},"context_markers":[{"label":"Lab","value":"Qwen (Alibaba Cloud)","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"qwenlm.github.io","source":"source"},{"label":"HN","value":"Community criticizes misleading naming and high VRAM usage despite fewer active parameters.","source":"source"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Model card","source":"model"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Infrastructure","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://qwenlm.github.io/blog/qwen-moe/"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-07T21:16:32.787981+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","dossier_json":"https://onlylabs.fyi/labs/qwen/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/qwen/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/qwen/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","evidence_focus":["post title","source URL","captured page text","HN traction","linked model or paper references","publication date"],"extraction_questions":["Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which writing reframes a recent release, model, hiring wave, or policy stance?","Which posts mention data, evals, infrastructure, safety, or deployment workflows?"],"signal_questions":["What public theme, launch framing, or research direction does this writing signal expose?","Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Do the 6 related writing signals show a repeated pattern?"],"output_fields":["org","theme","public_framing","traction","data_business_lane","evidence_url"],"data_business_relevance":"Public writing supplies the narrative layer over raw signals and helps identify which frontier-lab priorities are becoming externally legible.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","required":true},{"label":"source","url":"https://qwenlm.github.io/blog/qwen-moe/","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/qwen/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/qwen/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/signals.json","required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Qwen (Alibaba Cloud)'s writing signal \"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters\" for frontier lab strategy."},"semantic_triples":[{"subject":"Qwen (Alibaba Cloud)","predicate":"published","object":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","text":"Qwen (Alibaba Cloud) published Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"is classified as","object":"writing signal","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters is classified as writing signal."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"belongs to","object":"talking desk","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters belongs to talking desk."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has evidence coverage 1 captured evidence page."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has captured page count","object":"1","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has captured page count 1."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has readable page count","object":"1","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has readable page count 1."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has related signal count","object":"6","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has related signal count 6."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has analysis playbook objective","object":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has analysis playbook objective Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has source host","object":"qwenlm.github.io","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has source host qwenlm.github.io."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has lab","object":"Qwen (Alibaba Cloud)","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has lab Qwen (Alibaba Cloud)."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has signal desk","object":"talking","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has signal desk talking."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has source host","object":"qwenlm.github.io","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has source host qwenlm.github.io."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has hn","object":"Community criticizes misleading naming and high VRAM usage despite fewer active parameters.","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has hn Community criticizes misleading naming and high VRAM usage despite fewer active parameters.."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has watch term","object":"Eval methodology","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has watch term Eval methodology."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has watch term","object":"Model card","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has watch term Model card."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has watch term","object":"Data pipeline","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has watch term Data pipeline."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has watch term","object":"Infrastructure","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has watch term Infrastructure."}]},"intelligence":{"signal_desk":"talking","answer":"Qwen (Alibaba Cloud) published Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Community criticizes misleading naming and high VRAM usage despite fewer active parameters. · Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters | Qwen We have a new blog! View this page at qwen.ai . This page will automatically redirect in.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","semantic_triples":[{"subject":"Qwen (Alibaba Cloud)","predicate":"published","object":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","text":"Qwen (Alibaba Cloud) published Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"is classified as","object":"writing signal","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters is classified as writing signal."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"belongs to","object":"talking desk","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters belongs to talking desk."},{"subject":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters has evidence coverage 1 captured evidence page."}]},"signal":{"id":"d079a56b-4d3e-4862-9e10-bade69e26fa4","url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4","json_url":"https://onlylabs.fyi/signals/d079a56b-4d3e-4862-9e10-bade69e26fa4/signal.json","source_url":"https://qwenlm.github.io/blog/qwen-moe/","title":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","summary":"Qwen (Alibaba Cloud) published a writing signal. onlylabs watches public writing for research themes, product direction, and model-launch context.","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2024-03-28T03:31:44+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://qwenlm.github.io/blog/qwen-moe/"]},"facets":{},"traction":{"github_stars":null,"hn_points":104,"hn_comments":10,"hn_story_id":"39867551","hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"url":"https://qwenlm.github.io/blog/qwen-moe/","final_url":"https://qwenlm.github.io/blog/qwen-moe/","title":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","http_status":200,"content_type":"text/html; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-07T21:16:32.787981+00:00","bytes":44211,"raw_path":"b15b92c2aa2130e5563e50c70da7a5ee2aa00c4e095fffd4206793c1fc19b1cd.html","content_hash":"a24ccf79964837c368cc2b17ce9092e98af652d216bdf528ce7253f9946c9075","excerpt_chars":1200,"truncated":true,"excerpt":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters | Qwen We have a new blog! View this page at qwen.ai . This page will automatically redirect in 5 seconds. If you are not redirected automatically, please click the button below. Go Now Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters March 28, 2024 · 7 min · 1411 words · Qwen Team | Translations: 简体中文 GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction # Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.5-7B. Compared to Qwen1.5-7B, which contains 6.5 billion non-embedding parameters, Qwen1.5-MoE-A2.7B contains only 2.0 billion non-embedding parameters, approximately one-third of Qwen1.5-7B’s size. Notably, it achieves a 75% decrease in training expenses and..."},"evidence_pages":[{"url":"https://qwenlm.github.io/blog/qwen-moe/","final_url":"https://qwenlm.github.io/blog/qwen-moe/","title":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters","http_status":200,"content_type":"text/html; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-07T21:16:32.787981+00:00","bytes":44211,"raw_path":"b15b92c2aa2130e5563e50c70da7a5ee2aa00c4e095fffd4206793c1fc19b1cd.html","content_hash":"a24ccf79964837c368cc2b17ce9092e98af652d216bdf528ce7253f9946c9075","excerpt_chars":1200,"truncated":true,"excerpt":"Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters | Qwen We have a new blog! View this page at qwen.ai . This page will automatically redirect in 5 seconds. If you are not redirected automatically, please click the button below. Go Now Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters March 28, 2024 · 7 min · 1411 words · Qwen Team | Translations: 简体中文 GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction # Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.5-7B. Compared to Qwen1.5-7B, which contains 6.5 billion non-embedding parameters, Qwen1.5-MoE-A2.7B contains only 2.0 billion non-embedding parameters, approximately one-third of Qwen1.5-7B’s size. Notably, it achieves a 75% decrease in training expenses and..."}],"related_signals":[{"id":"54029233-5b0e-4748-aae1-6013ae3553d0","url":"https://onlylabs.fyi/signals/54029233-5b0e-4748-aae1-6013ae3553d0","source_url":"https://qwenlm.github.io/blog/qwen3guard/","title":"Qwen3Guard: Real-time Safety for Your Token Stream","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-09-22T20:00:00+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"},{"id":"4e64c872-3d4f-4d01-8908-35b65736eb6e","url":"https://onlylabs.fyi/signals/4e64c872-3d4f-4d01-8908-35b65736eb6e","source_url":"https://qwenlm.github.io/blog/qwen-image-edit/","title":"Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-08-18T17:30:00+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"},{"id":"27bd1b4a-28a4-423c-abb0-e5d24251de65","url":"https://onlylabs.fyi/signals/27bd1b4a-28a4-423c-abb0-e5d24251de65","source_url":"https://qwenlm.github.io/blog/qwen-image/","title":"Qwen-Image: Crafting with Native Text Rendering","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-08-04T14:08:30+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"},{"id":"c662ae5e-1dd9-42a6-8297-87bc670d59ef","url":"https://onlylabs.fyi/signals/c662ae5e-1dd9-42a6-8297-87bc670d59ef","source_url":"https://qwenlm.github.io/blog/gspo/","title":"GSPO: Towards Scalable Reinforcement Learning for Language Models","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-07-27T07:00:00+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"},{"id":"22c0d58c-5ce1-4d1f-97df-de5ebd764517","url":"https://onlylabs.fyi/signals/22c0d58c-5ce1-4d1f-97df-de5ebd764517","source_url":"https://qwenlm.github.io/blog/qwen-mt/","title":"Qwen-MT: Where Speed Meets Smart Translation","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-07-24T14:00:00+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"},{"id":"b6e0bdb2-ffd3-4aed-b44b-732a5e0424a5","url":"https://onlylabs.fyi/signals/b6e0bdb2-ffd3-4aed-b44b-732a5e0424a5","source_url":"https://qwenlm.github.io/blog/qwen3-coder/","title":"Qwen3-Coder: Agentic Coding in the World","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"qwen","name":"Qwen (Alibaba Cloud)","category":"frontier-lab"},"occurred_at":"2025-07-22T13:00:00+00:00","first_seen_at":"2026-06-05T05:42:59.088452+00:00","date_source":"rss.item_date"}]}