A New 34B Open Source LLM, Astonishing 78 Score in MMLU (GPT-4 MMLU:83)

In plain words

This open source large language model contains 34 billion parameters and achieves a score of 78 on the MMLU benchmark. It is designed for developers and researchers who need access to a capable language model without proprietary restrictions. The model is available on GitHub for those looking to work with or fine-tune a mid-sized open alternative to larger commercial systems.

written from the facts on this page · September 2026

• 
  I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

• WM
  We made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲161

  Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…

• 
  Kitten TTS – 25MB CPU-Only, Open-Source TTS Model2025 · github.com · ▲1,003

  Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…

• 
  Dream 7B2025 · hkunlp.github.io · ▲191

  Powerful Open Diffusion LLM, Beyond Autoregressive

• 
  LLM StatsOct 2025 · llm-stats.com · ▲293

  I was overspending on GPT-4o. It was really hard to compare different models I could switch to, so I built this LLM comparison tool. It shows leaderboards, pricing, and performance data across 100+ LLMs (including all major providers and open-source models). Key features: - Live pricing comparisons - Benchmark Scores (MMLU, HumanEval, GPQA, etc.) - Context length vs cost analysis - Speed/throughput tests across providers - Quality vs price visualizations - Open source (all data verifiable) Try it out: https://llmstats.com I'd like to know your opinion :) Tech stack: Next.js,…

• 
  Llama 3.3 70B2024 · developer.meta.com · ▲347

  Llama 405B-level performance, at a fraction of the cost

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 19d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 21d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲379

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Flowla▲1,119

  Digital sales rooms that wow buyers

  Growth · 2023 · flowla.com

• 
  Passionfroot Discovery▲962

  Discover & book top creators to promote your product

  Growth · 2023 · passionfroot.me

• 
  Re:catch▲939

  If Google Form & Calendly had a baby

  Growth · 2023 · recatch.cc

• 
  Pitch 2.0▲886

  Create, share and analyze presentations faster than ever

  Work · 2023 · pitch.com

• 
  LeadDelta 3.0▲883

  CRM built for modern teams & creators powered by AI

  AI · 2023 · leaddelta.com

• 
  SpeedVitals▲829

  Hi HN, I’m Kashish, one of the co-founders of SpeedVitals, a platform for testing & monitoring website performance with a major emphasis on Core Web Vitals. Until now, our platform has only focused on Synthetic/Lab testing, such as Lighthouse tests and TTFB tests. But now, we have developed a Real-User Monitoring platform that doubles up as a Web Analytics tool. One major feature we have that most RUM tools lack is Performance Audits. Just like Lighthouse audits work on Lab test data, our audits work across all the real-user visits and gives suggestions on what task to prioritize first.…

  Dev tools · 2023 · speedvitals.com