{"schema_version":"onlylabs.public_signal.v1","title":"Baseten Writing: Best Open Source Models For Post Training","description":"Baseten writing signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208","json_url":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208/signal.json","generated_at":"2026-09-09T23:15:09.873Z","evidence_latest_fetched_at":"2026-09-02T12:02:57.321307+00:00","signal_first_seen_at":"2026-09-02T12:01:45.497094+00:00","org":{"slug":"baseten","name":"Baseten","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/baseten","dossier_json_url":"https://onlylabs.fyi/labs/baseten/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208","signal_json":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208/signal.json","source":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","lab_dossier":"https://onlylabs.fyi/labs/baseten","lab_dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis":"https://onlylabs.fyi/analysis/baseten","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/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/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","data_business":null},"answer_pack":{"answer":"Baseten published Best Open Source Models For Post Training. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Substantive industry blog post on open-source post-training models. · Best open-source models for post-training Try GLM-5.3 today. Frontier intelligence at a fraction of the cost. Here AI models Best open-source models for post-training.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","signal_desk":"talking","source_context":{"source_url":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","source_host":"baseten.co","occurred_at":"2026-09-02T10:51:41+00:00","first_seen_at":"2026-09-02T12:01:45.497094+00:00","date_source":"sitemap.lastmod","context":null},"context_markers":[{"label":"Lab","value":"Baseten","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"baseten.co","source":"source"},{"label":"Notability","value":"Substantive industry blog post on open-source post-training models.","source":"signal"},{"label":"Watch term","value":"RL environments","source":"evidence"},{"label":"Watch term","value":"Infrastructure","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://www.baseten.co/blog/best-open-source-models-for-post-training/"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-09-02T12:02:57.321307+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208/signal.json","dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/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 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","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/8dd84285-f6fb-49cb-a423-7039fcdde208/signal.json","required":true},{"label":"source","url":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/baseten/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/baseten/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/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 Baseten's writing signal \"Best Open Source Models For Post Training\" for neocloud strategy."},"semantic_triples":[{"subject":"Baseten","predicate":"published","object":"Best Open Source Models For Post Training","text":"Baseten published Best Open Source Models For Post Training."},{"subject":"Best Open Source Models For Post Training","predicate":"is classified as","object":"writing signal","text":"Best Open Source Models For Post Training is classified as writing signal."},{"subject":"Best Open Source Models For Post Training","predicate":"belongs to","object":"talking desk","text":"Best Open Source Models For Post Training belongs to talking desk."},{"subject":"Best Open Source Models For Post Training","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Best Open Source Models For Post Training has evidence coverage 1 captured evidence page."},{"subject":"Best Open Source Models For Post Training","predicate":"has captured page count","object":"1","text":"Best Open Source Models For Post Training has captured page count 1."},{"subject":"Best Open Source Models For Post Training","predicate":"has readable page count","object":"1","text":"Best Open Source Models For Post Training has readable page count 1."},{"subject":"Best Open Source Models For Post Training","predicate":"has related signal count","object":"6","text":"Best Open Source Models For Post Training has related signal count 6."},{"subject":"Best Open Source Models For Post Training","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":"Best Open Source Models For Post Training 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":"Best Open Source Models For Post Training","predicate":"has source host","object":"baseten.co","text":"Best Open Source Models For Post Training has source host baseten.co."},{"subject":"Best Open Source Models For Post Training","predicate":"has lab","object":"Baseten","text":"Best Open Source Models For Post Training has lab Baseten."},{"subject":"Best Open Source Models For Post Training","predicate":"has signal desk","object":"talking","text":"Best Open Source Models For Post Training has signal desk talking."},{"subject":"Best Open Source Models For Post Training","predicate":"has source host","object":"baseten.co","text":"Best Open Source Models For Post Training has source host baseten.co."},{"subject":"Best Open Source Models For Post Training","predicate":"has notability","object":"Substantive industry blog post on open-source post-training models.","text":"Best Open Source Models For Post Training has notability Substantive industry blog post on open-source post-training models.."},{"subject":"Best Open Source Models For Post Training","predicate":"has watch term","object":"RL environments","text":"Best Open Source Models For Post Training has watch term RL environments."},{"subject":"Best Open Source Models For Post Training","predicate":"has watch term","object":"Infrastructure","text":"Best Open Source Models For Post Training has watch term Infrastructure."},{"subject":"Best Open Source Models For Post Training","predicate":"has watch term","object":"Agents and tool use","text":"Best Open Source Models For Post Training has watch term Agents and tool use."}]},"intelligence":{"signal_desk":"talking","answer":"Baseten published Best Open Source Models For Post Training. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Substantive industry blog post on open-source post-training models. · Best open-source models for post-training Try GLM-5.3 today. Frontier intelligence at a fraction of the cost. Here AI models Best open-source models for post-training.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","semantic_triples":[{"subject":"Baseten","predicate":"published","object":"Best Open Source Models For Post Training","text":"Baseten published Best Open Source Models For Post Training."},{"subject":"Best Open Source Models For Post Training","predicate":"is classified as","object":"writing signal","text":"Best Open Source Models For Post Training is classified as writing signal."},{"subject":"Best Open Source Models For Post Training","predicate":"belongs to","object":"talking desk","text":"Best Open Source Models For Post Training belongs to talking desk."},{"subject":"Best Open Source Models For Post Training","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Best Open Source Models For Post Training has evidence coverage 1 captured evidence page."}]},"signal":{"id":"8dd84285-f6fb-49cb-a423-7039fcdde208","url":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208","json_url":"https://onlylabs.fyi/signals/8dd84285-f6fb-49cb-a423-7039fcdde208/signal.json","source_url":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","title":"Best Open Source Models For Post Training","summary":"Baseten 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":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-02T10:51:41+00:00","first_seen_at":"2026-09-02T12:01:45.497094+00:00","date_source":"sitemap.lastmod","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://www.baseten.co/blog/best-open-source-models-for-post-training/"]},"facets":{},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"is_primary":true,"source_match":true,"url":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","final_url":"https://www.baseten.co/blog/best-open-source-models-for-post-training/","title":"Best Open Source Models For Post Training","http_status":200,"content_type":"text/html; charset=utf-8","capture_method":"plain","fetched_at":"2026-09-02T12:02:57.321307+00:00","bytes":332380,"raw_path":"a189af82fcdac8e73a2b6e483df1e8d389a276144b8bdb6cb71ae87989b1f1a1.html","content_hash":"ef1dcd5e92d49392685baaaebc38f32c3acd60b0160957a342230c841617c66c","excerpt_chars":1200,"truncated":true,"excerpt":"Best open-source models for post-training Try GLM-5.3 today. Frontier intelligence at a fraction of the cost. Here AI models Best open-source models for post-training Compare top open-source models for post-training. Learn what drives cost and which model fits use case. Authors Chloe Florit Last updated September 2, 2026 Share TL;DR Choosing an open-source model for post-training comes down to cost and use case. Cost is driven by active parameters, total parameters, and KV cache size. We grouped the best models into five cost tiers, from ultra-expensive (Kimi K3) to ultra-cheap (Qwen3.6-35B-A3B), and explained which to pick for text, vision, and coding-agent work. DeepSeek-V4-Flash is great for long-context, cost-sensitive tasks; GLM-5.2 provides fast, asynchronous RL; Kimi K2.6 and K2.7 Code fine-tune the most stably, with K2.7 best for coding agents; Nemotron-3-Super-120B is efficient to fine-tune with native FP4; and Qwen3 is the safe default with the widest size and library support. During post-training, an open-source model can be specialized for your use case with methods like supervised fine-tuning, preference optimization, and reinforcement learning (RL). RL is one of the..."},"evidence_pages":[],"related_signals":[{"id":"7b42fac2-f048-41b3-9275-349c47f2335a","url":"https://onlylabs.fyi/signals/7b42fac2-f048-41b3-9275-349c47f2335a","source_url":"https://www.baseten.co/blog/how-baseten-makes-pyannotes-diarization-models-96x-faster/","title":"How Baseten Makes Pyannotes Diarization Models 96x Faster","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-09T00:00:00+00:00","first_seen_at":"2026-09-09T20:00:53.077479+00:00","date_source":"sitemap.lastmod"},{"id":"5a040dc3-5085-482d-bb70-4e9096d0e574","url":"https://onlylabs.fyi/signals/5a040dc3-5085-482d-bb70-4e9096d0e574","source_url":"https://www.baseten.co/blog/optimizing-delta-weight-syncs-for-managed-rollouts/","title":"Optimizing Delta Weight Syncs For Managed Rollouts","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-08T22:36:24+00:00","first_seen_at":"2026-09-09T00:00:51.730848+00:00","date_source":"sitemap.lastmod"},{"id":"4bc6b810-0677-4409-a1bb-b8d733ecb37b","url":"https://onlylabs.fyi/signals/4bc6b810-0677-4409-a1bb-b8d733ecb37b","source_url":"https://www.baseten.co/blog/baseten-leads-covals-voice-ai-benchmark/","title":"Baseten Leads Covals Voice Ai Benchmark","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-08T22:20:40+00:00","first_seen_at":"2026-09-09T00:00:51.730848+00:00","date_source":"sitemap.lastmod"},{"id":"3af4f3d3-59a4-4686-94ba-6b6cacdd1091","url":"https://onlylabs.fyi/signals/3af4f3d3-59a4-4686-94ba-6b6cacdd1091","source_url":"https://www.baseten.co/blog/new-mcp-and-skill-for-coding-agents-to-use-baseten/","title":"New Mcp And Skill For Coding Agents To Use Baseten","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-02T18:20:19+00:00","first_seen_at":"2026-09-02T20:00:52.042916+00:00","date_source":"sitemap.lastmod"},{"id":"9848b185-9578-4f96-8911-a25dba91ec70","url":"https://onlylabs.fyi/signals/9848b185-9578-4f96-8911-a25dba91ec70","source_url":"https://www.baseten.co/blog/the-efficient-frontier-of-llm-inference/","title":"The Efficient Frontier Of Llm Inference","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-01T23:47:31+00:00","first_seen_at":"2026-09-02T00:00:51.666285+00:00","date_source":"sitemap.lastmod"},{"id":"54f6a3fb-74e2-45ec-98c7-ee266104b764","url":"https://onlylabs.fyi/signals/54f6a3fb-74e2-45ec-98c7-ee266104b764","source_url":"https://www.baseten.co/resources/changelog/viewer-role-for-read-only-access/","title":"Viewer Role For Read Only Access","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-01T20:18:10+00:00","first_seen_at":"2026-09-02T00:00:51.666285+00:00","date_source":"sitemap.lastmod"}]}