{"schema_version":"onlylabs.public_signal.v1","title":"Cerebras Model: cerebras/GLM-4.6-REAP-252B-A32B","description":"Cerebras model signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251","json_url":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251/signal.json","generated_at":"2026-06-11T02:49:54.321398+00:00","org":{"slug":"cerebras","name":"Cerebras","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/cerebras","dossier_json_url":"https://onlylabs.fyi/labs/cerebras/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251","signal_json":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251/signal.json","source":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B","lab_dossier":"https://onlylabs.fyi/labs/cerebras","lab_dossier_json":"https://onlylabs.fyi/labs/cerebras/dossier.json","analysis":"https://onlylabs.fyi/analysis/cerebras","analysis_json":"https://onlylabs.fyi/analysis/cerebras/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cerebras/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":"https://onlylabs.fyi/topics/releases","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml?category=neocloud","data_business":null},"answer_pack":{"answer":"Cerebras published cerebras/GLM-4.6-REAP-252B-A32B. This model signal is evidence of what shipped on model infrastructure and how the release is positioned. High-signal details: license mit · 8 HF downloads · Low traction releases, minor despite size.. onlylabs links this event to 1 captured evidence page and 6 related model signals.","signal_desk":"releases","source_context":{"source_url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B","source_host":"huggingface.co","occurred_at":"2025-10-24T00:22:05+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source","context":null},"context_markers":[{"label":"Lab","value":"Cerebras","source":"signal"},{"label":"Signal desk","value":"releases","source":"signal"},{"label":"Source host","value":"huggingface.co","source":"source"},{"label":"Task","value":"text-generation","source":"model"},{"label":"License","value":"mit","source":"model"},{"label":"Library","value":"transformers","source":"model"},{"label":"Params","value":"252B","source":"model"},{"label":"Downloads","value":"8","source":"traction"},{"label":"Likes","value":"4","source":"traction"},{"label":"Notability","value":"Low traction releases, minor despite size.","source":"signal"},{"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":"Agents and tool use","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://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T02:49:54.321398+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251/signal.json","dossier_json":"https://onlylabs.fyi/labs/cerebras/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/cerebras/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cerebras/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml?category=neocloud","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","evidence_focus":["model card","release note","version or tag","pipeline tag","license","downloads, likes, stars, and linked papers"],"extraction_questions":["What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Which launches create new eval, data, infra, or deployment needs?","Which shipped signals are missing captured page context?"],"signal_questions":["What shipped in this model artifact, and what evidence describes its capability, license, or traction?","What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Do the 6 related model signals show a repeated pattern?"],"output_fields":["org","release_type","artifact","traction","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251/signal.json","required":true},{"label":"source","url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/cerebras/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/cerebras/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/releases/signals.json?category=neocloud","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 Cerebras's model signal \"cerebras/GLM-4.6-REAP-252B-A32B\" for neocloud strategy."},"semantic_triples":[{"subject":"Cerebras","predicate":"published model","object":"cerebras/GLM-4.6-REAP-252B-A32B","text":"Cerebras published model cerebras/GLM-4.6-REAP-252B-A32B."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"is classified as","object":"model signal","text":"cerebras/GLM-4.6-REAP-252B-A32B is classified as model signal."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"belongs to","object":"releases desk","text":"cerebras/GLM-4.6-REAP-252B-A32B belongs to releases desk."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has evidence coverage","object":"1 captured evidence page","text":"cerebras/GLM-4.6-REAP-252B-A32B has evidence coverage 1 captured evidence page."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has captured page count","object":"1","text":"cerebras/GLM-4.6-REAP-252B-A32B has captured page count 1."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has readable page count","object":"1","text":"cerebras/GLM-4.6-REAP-252B-A32B has readable page count 1."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has related signal count","object":"6","text":"cerebras/GLM-4.6-REAP-252B-A32B has related signal count 6."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has analysis playbook objective","object":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","text":"cerebras/GLM-4.6-REAP-252B-A32B has analysis playbook objective Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has source host","object":"huggingface.co","text":"cerebras/GLM-4.6-REAP-252B-A32B has source host huggingface.co."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has lab","object":"Cerebras","text":"cerebras/GLM-4.6-REAP-252B-A32B has lab Cerebras."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has signal desk","object":"releases","text":"cerebras/GLM-4.6-REAP-252B-A32B has signal desk releases."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has source host","object":"huggingface.co","text":"cerebras/GLM-4.6-REAP-252B-A32B has source host huggingface.co."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has task","object":"text-generation","text":"cerebras/GLM-4.6-REAP-252B-A32B has task text-generation."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has license","object":"mit","text":"cerebras/GLM-4.6-REAP-252B-A32B has license mit."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has library","object":"transformers","text":"cerebras/GLM-4.6-REAP-252B-A32B has library transformers."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has params","object":"252B","text":"cerebras/GLM-4.6-REAP-252B-A32B has params 252B."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has downloads","object":"8","text":"cerebras/GLM-4.6-REAP-252B-A32B has downloads 8."}]},"intelligence":{"signal_desk":"releases","answer":"Cerebras published cerebras/GLM-4.6-REAP-252B-A32B. This model signal is evidence of what shipped on model infrastructure and how the release is positioned. High-signal details: license mit · 8 HF downloads · Low traction releases, minor despite size.. onlylabs links this event to 1 captured evidence page and 6 related model signals.","semantic_triples":[{"subject":"Cerebras","predicate":"published model","object":"cerebras/GLM-4.6-REAP-252B-A32B","text":"Cerebras published model cerebras/GLM-4.6-REAP-252B-A32B."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"is classified as","object":"model signal","text":"cerebras/GLM-4.6-REAP-252B-A32B is classified as model signal."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"belongs to","object":"releases desk","text":"cerebras/GLM-4.6-REAP-252B-A32B belongs to releases desk."},{"subject":"cerebras/GLM-4.6-REAP-252B-A32B","predicate":"has evidence coverage","object":"1 captured evidence page","text":"cerebras/GLM-4.6-REAP-252B-A32B has evidence coverage 1 captured evidence page."}]},"signal":{"id":"b3002612-c5a8-47f4-8571-a2e227233251","url":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251","json_url":"https://onlylabs.fyi/signals/b3002612-c5a8-47f4-8571-a2e227233251/signal.json","source_url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B","title":"cerebras/GLM-4.6-REAP-252B-A32B","summary":"Cerebras published a model signal. onlylabs watches model cards, launch context, and traction.","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-10-24T00:22:05+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source","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://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md"]},"facets":{"pipeline_tag":"text-generation","license":"mit"},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":8,"hf_likes":4},"data_radar":null},"primary_evidence_page":{"url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md","final_url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md","title":"cerebras/GLM-4.6-REAP-252B-A32B model card","http_status":200,"content_type":"text/plain; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-11T02:49:54.321398+00:00","bytes":5924,"raw_path":"fa4e89487aa31b395016ddc05181e12f50b2d686ec497d9e94d45161a5022df7.md","content_hash":"3c42ba9d54fad4e03ee58d0fa91cffcc14a59f4dbf1bf69d2fd278270dceccc5","excerpt_chars":1200,"truncated":true,"excerpt":"--- language: - en library_name: transformers tags: - glm - MOE - pruning - compression license: mit name: cerebras/GLM-4.6-REAP-252B-A32B description: > This model was obtained by uniformly pruning 30% of experts in GLM-4.6 using the REAP method. readme: > https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/main/README.md license_link: https://huggingface.co/zai-org/GLM-4.6/blob/main/LICENSE pipeline_tag: text-generation base_model: - zai-org/GLM-4.6 --- <p align=\"center\"> <em>𓌳 <strong>REAP</strong>𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression</em><br> <img src=\"https://i.imgur.com/rmzG3gg.png\" alt=\"REAP\" width=\"75%\"> </p> GLM-4.6-REAP-252B-A32B ✨ Highlights Introducing **GLM-4.6-REAP-252B-A32B**, a **memory-efficient compressed variant** of GLM-4.6 that maintains near-identical performance while being **30% lighter**. **Note: this is a BF16 version for more accurate downstream low-bit quantization. An [FP8 version](https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B-FP8) is also available on HF.** This model was created using **REAP (Router-weighted Expert Activation Pruning)**, a novel expert pruning method that selectively removes redundant experts..."},"evidence_pages":[{"url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md","final_url":"https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/raw/main/README.md","title":"cerebras/GLM-4.6-REAP-252B-A32B model card","http_status":200,"content_type":"text/plain; charset=utf-8","capture_method":"plain","fetched_at":"2026-06-11T02:49:54.321398+00:00","bytes":5924,"raw_path":"fa4e89487aa31b395016ddc05181e12f50b2d686ec497d9e94d45161a5022df7.md","content_hash":"3c42ba9d54fad4e03ee58d0fa91cffcc14a59f4dbf1bf69d2fd278270dceccc5","excerpt_chars":1200,"truncated":true,"excerpt":"--- language: - en library_name: transformers tags: - glm - MOE - pruning - compression license: mit name: cerebras/GLM-4.6-REAP-252B-A32B description: > This model was obtained by uniformly pruning 30% of experts in GLM-4.6 using the REAP method. readme: > https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B/main/README.md license_link: https://huggingface.co/zai-org/GLM-4.6/blob/main/LICENSE pipeline_tag: text-generation base_model: - zai-org/GLM-4.6 --- <p align=\"center\"> <em>𓌳 <strong>REAP</strong>𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression</em><br> <img src=\"https://i.imgur.com/rmzG3gg.png\" alt=\"REAP\" width=\"75%\"> </p> GLM-4.6-REAP-252B-A32B ✨ Highlights Introducing **GLM-4.6-REAP-252B-A32B**, a **memory-efficient compressed variant** of GLM-4.6 that maintains near-identical performance while being **30% lighter**. **Note: this is a BF16 version for more accurate downstream low-bit quantization. An [FP8 version](https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B-FP8) is also available on HF.** This model was created using **REAP (Router-weighted Expert Activation Pruning)**, a novel expert pruning method that selectively removes redundant experts..."}],"related_signals":[{"id":"c043795d-d639-4f88-95c4-49025226c41b","url":"https://onlylabs.fyi/signals/c043795d-d639-4f88-95c4-49025226c41b","source_url":"https://huggingface.co/cerebras/Step-3.5-Flash-REAP-121B-A11B","title":"cerebras/Step-3.5-Flash-REAP-121B-A11B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-02-25T07:11:20+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"},{"id":"8e156f68-4602-4639-a2fe-608bfd8b83af","url":"https://onlylabs.fyi/signals/8e156f68-4602-4639-a2fe-608bfd8b83af","source_url":"https://huggingface.co/cerebras/Step-3.5-Flash-REAP-149B-A11B","title":"cerebras/Step-3.5-Flash-REAP-149B-A11B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-02-25T07:05:37+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"},{"id":"4853c7eb-6324-4e2c-9738-37b91aac9725","url":"https://onlylabs.fyi/signals/4853c7eb-6324-4e2c-9738-37b91aac9725","source_url":"https://huggingface.co/cerebras/GLM-4.7-Flash-REAP-23B-A3B","title":"cerebras/GLM-4.7-Flash-REAP-23B-A3B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-01-23T05:26:34+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"},{"id":"1fa7b9fc-581e-4b68-ba55-7d2a6fe8a66e","url":"https://onlylabs.fyi/signals/1fa7b9fc-581e-4b68-ba55-7d2a6fe8a66e","source_url":"https://huggingface.co/cerebras/GLM-4.7-REAP-218B-A32B","title":"cerebras/GLM-4.7-REAP-218B-A32B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-01-10T20:39:01+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"},{"id":"4b7077fd-5f99-4436-8f33-64f484682473","url":"https://onlylabs.fyi/signals/4b7077fd-5f99-4436-8f33-64f484682473","source_url":"https://huggingface.co/cerebras/GLM-4.7-REAP-268B-A32B","title":"cerebras/GLM-4.7-REAP-268B-A32B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-01-10T20:34:42+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"},{"id":"65aa0627-3cbf-453f-98f2-186a94b643f0","url":"https://onlylabs.fyi/signals/65aa0627-3cbf-453f-98f2-186a94b643f0","source_url":"https://huggingface.co/cerebras/DeepSeek-V3.2-REAP-345B-A37B","title":"cerebras/DeepSeek-V3.2-REAP-345B-A37B","context":null,"kind":{"key":"model_released","label":"Model"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-12-09T13:48:42+00:00","first_seen_at":"2026-06-06T01:49:47.331765+00:00","date_source":"source"}]}