1/5 Releasing Jamba Reasoning 3B under Apache 2.0: Hybrid SSM-Transformer architecture that tops accuracy & speed across record context lengths. e.g. 3-5X faster than Llama 3.2 3B and Qwen3 4B at 32K tokens.
OPEN SOURCE
-
Ollama Alternatives: LMStudio, Llama.cpp, vLLM and More
By
–
ollama alternatives > lmstudio
> llama.cpp
> exllamav2/v3
> vllm
> sglang among many others like literally anything is better than ollama lmao -
QuestA: Expanding LLM Reasoning via Question Augmentation
By
–
#PapersAccepted by Jiqizhixin
Our report: https://
mp.weixin.qq.com/s/Mhy9fWM8KVnu
3mTy7I3osQ
… QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation Tsinghua University, Shanghai Qi Zhi Institute, and others
Paper: https://
arxiv.org/abs/2507.13266
Models: https://
huggingface.co/foreverlasting
1202/QuestA-Nemotron-1.5B
…
Code: -
Python 3.14 Released: Open Source Library Maintainers Can Drop 3.9
By
–
Python 3.14 is out today! Here are my notes on the new release: https://
simonwillison.net/2025/Oct/8/pyt
hon-314/
… If you're an open source library maintainer who supports all current Python releases this also means you can drop 3.9 support now and start depending on features from 3.10, like match/case -
Open-source speech-to-text component for web applications
By
–
☑️transcriber-01
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 8 octobre 2025
🎙️ Want instant speech-to-text inside your web app?
Meet transcriber-01 — an open-source voice dictation component you can drop right into your workflow.
It’s lightweight, accurate, and made for developers who love speed. pic.twitter.com/BKrEHpzOKXtranscriber-01 Want instant speech-to-text inside your web app? Meet transcriber-01 — an open-source voice dictation component you can drop right into your workflow.
It’s lightweight, accurate, and made for developers who love speed. -
ElevenLabs Launches Open-Source UI Components for Voice Agents
By
–
🚨ElevenLabs UI Launch
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 8 octobre 2025
🚀 Building with AI audio or voice agents just got easier.
ElevenLabs just dropped ElevenLabs UI — a full set of open-source components for devs.
◽️22 pre-built modules for chat, transcription, and music
◽️Fully customizable
◽️MIT-licensed and ready to… pic.twitter.com/WtZ6IkPo4zElevenLabs UI Launch Building with AI audio or voice agents just got easier. ElevenLabs just dropped ElevenLabs UI — a full set of open-source components for devs. 22 pre-built modules for chat, transcription, and music
Fully customizable
MIT-licensed and ready to -
Scaling TorchTitan with SkyPilot Community Tutorials
By
–
More ways to scale TorchTitan with SkyPilot great to see the community expanding the ecosystem with new tutorials like this one!
-
Open Weights Models Secured Against Permanent Loss
By
–
open weights already backed up, boy will never retire
-
LFM2-8B-A1B GGUF Quantizations Available on Hugging Face
By
–
LFM2-8B-A1B and GGUF quants are now available on Hugging Face!
-
LFM2-8B-A1B: Efficient MoE Language Model Released
By
–
LFM2-8B-A1B just dropped on @huggingface!
— Maxime Labonne @ ICLR (@maximelabonne) 7 octobre 2025
8.3B params with only 1.5B active/token 🚀
> Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B
> MoE designed to run on phones/laptops (llama.cpp / vLLM)
> Pre-trained on 12T tokens → strong math/code/IF pic.twitter.com/cGbuJoOMDNLFM2-8B-A1B just dropped on @huggingface
! 8.3B params with only 1.5B active/token > Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B
> MoE designed to run on phones/laptops (llama.cpp / vLLM)
> Pre-trained on 12T tokens → strong math/code/IF