Entity trail

Olmo Hybrid

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-03-16 / hn-researcherLLM Architecture Gallery — 45+ Model Diagrams Surges to 443pts, 34cmtsSebastian Raschka's LLM Architecture Gallery hit 443 points after posting March 15-16, covering architecture diagrams and fact sheets for 45+ models from 3B to 1T parameters. Covers dense models (Llama 3, Gemma 3, OLMo 3), sparse MoE (DeepSeek V3/V3.2, Llama 4 Maverick, Mistral 3 Large), and hybrid architectures (Qwen3 Next, Kimi Linear) with parameter counts, release dates, attention type, and technical report links. Physical high-resolution poster available.
2026-03-07 / thought-leaders-researcherLambert Olmo Hybrid Architecture AnalysisLambert argues transformer-only era may be ending. OLMo Hybrid formally proves hybrid models solve problems neither transformers nor GDN can solve alone.
2026-03-07 / rss-researcherOlmo Hybrid 7B: Transformers + Linear RNNs for 2x Data EfficiencyAI2 released Olmo Hybrid 7B, a fully open model using a 3:1 DeltaNet-to-attention architecture that replaces 75% of attention with Gated DeltaNet layers. Trained on 6T tokens across 512 GPUs (H100s then B200s). Achieves same MMLU accuracy as Olmo 3 with 49% fewer tokens — roughly 2x data efficiency. Full code, training configs, and launch scripts open-sourced. Nathan Lambert's analysis on Interconnects positions this as evidence that hybrid architectures may dominate future LLM design. Interconn
2026-03-07 / projects-researcherallenai/OLMo-core + Olmo-Hybrid-7BAI2 released Olmo Hybrid 7B on March 6 -- a fully open 7B model combining transformer attention with linear recurrent layers (Gated DeltaNet). Uses 3:1 pattern: three DeltaNet sublayers followed by one multihead attention sublayer, replacing 75% of attention with linear recurrence. Achieves 2x data efficiency over Olmo 3 on MMLU (same accuracy with 49% fewer tokens). Trained on 6T tokens on 512 GPUs (H100s then B200s at Lambda). Releases base, SFT, DPO stages with all weights, checkpoints, train
2026-03-06 / news-researcherAI2 Releases OLMo Hybrid 7B 2x Data EfficiencyFully open 7B model combining transformer attention with Gated DeltaNet layers achieves same MMLU with 49% fewer tokens. 85.0 on RULER 64K vs OLMo 3 70.9.

Graph relationships

BENCHMARKED AGAINST
GDN
OLMo Hybrid formally proves it solves problems GDN cannot solve alone.
Source finding
BENCHMARKED AGAINST
Transformer
OLMo Hybrid formally proves it solves problems transformers cannot solve alone.
Source finding

Source trail

Bitdefender NVIDIA Claude Code Docs Anthropic Google AI2 TechCrunch – GPT-5.4 Simon Willison – Codex for OSS VKTR – Claude Auto Mode The Hacker News – CyberStrikeAI TechCrunch – Google Canvas 9to5Mac – Siri Delays

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…