Aleph Alpha Open-Sources Kolibri-1

Episode 1 · Aleph Alpha open-sources Kolibri-1: a 78B MoE with only 3.46B active params (2026-10-03, 14 posts)

German AI company Aleph Alpha open-sourced its reasoning MoE model Kolibri-1 on Hugging Face on October 3 (German Unity Day), where it quickly trended. Under the Apache 2.0 license, it is positioned as a sovereign, European open-weight model: trained from scratch entirely in Germany, not a Qwen fine-tune, with a focus on German and English bilingual capability after months of pre- and post-training.

Confirmed

• Specs: 78.1B total parameters, only 3.46B active per token (4.4%), context length up to 1M tokens
• Architecture details (per @TejasKumar): 384 small experts per layer, with the router activating 6 per token — roughly 3.5B parameters running per word
• Benchmark performance (per @TejasKumar): 96.9% on AIME 2025, beating all tested MoE models of similar or larger size, including those with more active parameters per token
• Release format: available in vLLM and safetensors formats with an accompanying arXiv paper; weights can run on users' own hardware. Per @QuixiAI, the weights are in FP8 and run directly, and a feature request has already been filed for support in the open-source inference engine colibri (39.5k stars)
• The model repo includes chat template configuration supporting system prompts, reasoning effort settings, and tool-calling format (per @JiliJeanlouis)
• Third party Tesseracted Labs is hosting the model, letting users try it free in the browser for a few days without GPU or registration, with Brave Search web search enabled (per @FrankNoeBerlin)

Unconfirmed

• Benchmarks such as the 96.9% AIME score currently come mainly from the publisher's materials and relayers like @TejasKumar, and await independent third-party verification

Why it matters

• This is a flagship open-source result for Europe's "sovereign AI" route: trained and released entirely in Germany, offering Europe a controllable option independent of the US and China
• The very low activation ratio (4.4%) implies much lower inference cost; if the benchmarks hold up under third-party testing, it will be a strong contender in the efficient-reasoning track
• Free third-party trial access lowers the barrier to entry and helps the community build independent evaluations quickly

• Aleph Alpha's sovereign open-weight Kolibri scores 96.9% on AIME, beating 3x bigger MoE models — TejasKumar_ · 2026-10-03
• Aleph Alpha launches Kolibri, an Apache 2.0 sovereign open-weight LLM built in Germany — TejasKumar_ · 2026-10-03
• Aleph Alpha open-sources Kolibri-1: 78B MoE with 3.46B active params and 1M context — Nunki08 · 2026-10-03
• Aleph-Alpha's MoE reasoning model Kolibri-1 trends on Hugging Face — Aleph-Alpha · 2026-10-03
• Aleph Alpha open-sources Kolibri: 78.1B MoE with 3.46B active params under Apache 2.0 — petrusenko_max · 2026-10-04
• Aleph Alpha open-sources Kolibri-1 model on Hugging Face — JiliJeanlouis · 2026-10-04
• Germany's sovereign open-weight Kolibri: 78B params, 3.5B active, 96.9% on AIME 2025 — TejasKumar_ · 2026-10-04
• Aleph Alpha Releases Kolibri: a From-Scratch 78B MoE With Only 3.46B Active Params, Apache 2.0 — solyarisoftware · 2026-10-04
• Aleph Alpha open-sources German sovereign model Kolibri-1, free to try in browser — FrankNoeBerlin · 2026-10-04
• Aleph Alpha open-sources Kolibri: 78B MoE with 3B active params and 1M context, Apache 2.0 — TejasKumar_ · 2026-10-04
• Aleph Alpha open-sources Kolibri: 78B params, 3.46B active, 1M context, Apache 2.0 — josh_wills · 2026-10-04
• Aleph Alpha releases open-weight European model Kolibri-1 under Apache 2.0 — PMinervini · 2026-10-04
• Aleph Alpha's Kolibri-1: 78B MoE with 3B active params, native FP8 weights — QuixiAI · 2026-10-05
• Stealthy German lab Aleph Alpha drops open-weight Kolibri: 78B params, 3.46B active, 1M context — skdh · 2026-10-05

Episode 2 · Aleph Alpha Open-Sources Kolibri: 78B-Parameter Model with 1M Context (2026-10-05, 3 posts)

Germany's Aleph Alpha has open-sourced Kolibri, a 78.1B-parameter German-English MoE model under Apache 2.0 that activates only about 3.46B parameters per token and supports up to 1M-token context. Positioned for European sovereign use cases, it is seen as surpassing Mistral.

• Aleph Alpha releases Kolibri: sovereign open-weight 78B model with 1M context — TorturedPoet30 · 2026-10-05
• Aleph Alpha open-sources Kolibri: 78B params, 3.46B active, 1M context — as Mistral cedes the sovereign AI crown — irombie · 2026-10-05
• Aleph Alpha open-sources Kolibri-1: a 78.1B MoE with just 3.46B active params per token — lmoroney · 2026-10-06