{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-11-12-edge0-145b-on-device-open-model/","md":"https://postcutoff.com/e/2026-11-12-edge0-145b-on-device-open-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-11-12-edge0-145b-on-device-open-model","date":"2026-11-12","date_precision":"day","short_title":"Edge0 releases Edge0-145B, an open 145B-parameter MoE model built to run on a 48 GB laptop","deck":null,"takeaway":"On Nov 12, 2026 Edge0 released Edge0-145B, a 145B-parameter mixture-of-experts model with about 10B active parameters, designed from the start for local hardware: about 29 GB peak memory, 80+ tokens/s decode and a 128K-256K context on laptops such as a MacBook Pro.","category":"open-source","category_label":"Open source","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":[{"n":1,"title":"Edge0: Introducing Edge0-145B","url":"https://edge0.ai/blog/introducing-edge0-145b-frontier-ai-capabilities-on-your-own-computer","type":"official","group":"primary","domain":"edge0.ai"},{"n":2,"title":"Hugging Face: Edge0/Edge0-145B-NVFP4","url":"https://huggingface.co/Edge0/Edge0-145B-NVFP4","type":"code","group":"primary","domain":"huggingface.co"},{"n":3,"title":"Hacker News discussion","url":"https://news.ycombinator.com/item?id=50475713","type":"discussion","group":"reactions","domain":"news.ycombinator.com"}],"official":2,"filed":"2026-11-13","updated":"2026-11-13","orgs":["Edge0"],"title":"Edge0 releases Edge0-145B, an open 145B-parameter MoE model built to run on a 48 GB laptop","summary":"On Nov 12, 2026 Edge0 released Edge0-145B, a 145B-parameter mixture-of-experts model with about 10B active parameters, designed from the start for local hardware: about 29 GB peak memory, 80+ tokens/s decode and a 128K-256K context on laptops such as a MacBook Pro. Weights (NVFP4) are on Hugging Face. Edge0's own benchmarks put it near DeepSeek-V4-Flash; no independent results yet.","key_facts":["Architecture: 145B total / ~10B active; groups of 64 sparse experts share two large matrices, each expert keeps small private parameters","Runtime (vendor): ~29 GB peak memory (28 GB elsewhere on the page), 80+ tok/s decode, 1,100+ tok/s prefill, ~120 W; macOS, Windows, Linux; Apple M-series and Nvidia RTX","Vendor benchmarks: DeepSWE 1.1 64.6 (DeepSeek-V4-Flash-0731 54.4); Terminal-Bench 2.1 86.52; GPQA-Diamond 90.4; HLE 35.4; six-benchmark mean 72.8 vs 71.7 for Qwen3.8-Flash-Next","Weights: huggingface.co/Edge0/Edge0-145B-NVFP4; inference code github.com/Edge0-AI/Edge0; the announcement says 'open-source' but names no licence","Hacker News: 275 points (Nov 12)"],"key_numbers":[],"tags":["open-weights","on-device","moe","local-models","nvfp4"],"science":null,"body_md":"## What happened\n\nEdge0 claims \"the world's first open-source on-device AI model with 145 billion parameters\". It was trained in its on-device\narchitecture rather than compressed afterwards. No registry file yet: the licence and independent evaluations are missing.\n\n## Why it matters\n\nIf the vendor numbers hold, near-2026-frontier-flash quality would run offline on a high-end laptop.","disputed":[],"related":[{"id":"2026-11-05-thinking-machines-inkling-2-small","url":"https://postcutoff.com/e/2026-11-05-thinking-machines-inkling-2-small/","date":"2026-11-05","date_precision":"day","short_title":"Thinking Machines Lab releases Inkling 2 Small on Tinker","deck":"Apache-2.0 weights followed on Nov 12 after safety testing","takeaway":"With the weights out (Nov 12) it is the strongest US open-weights model by Artificial Analysis' estimate; our open-weights pick stays Kimi K3.1 Pro, which scores higher (AA v5 46 vs ~31).","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":3,"filed":"2026-11-06","updated":"2026-11-15","orgs":["Thinking Machines Lab"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-11-13","type":"filed","text":"Created (news agent)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-13","run":null,"sources_read":null,"updated":"2026-11-13","human_review":null,"version":{"date":"2026-11-13"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":165,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":135,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":226,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":165,"in_training_data":false}],"short_url":null}