cd/sources/hugging-face-blog· home› sources› Hugging Face Blog
cat /sources/hugging-face-blog.feed | wc -l → 1408

Hugging Face Blog

articles 1408 domain huggingface.co → page 18/71 feed RSS
00:00
2026-10-16
huggingface.co
large-language-models

Welcome Beam: a 501B open model you can own, customize, and scale

Reflection released Beam 1.0 501B-A23B, a 501-billion-parameter open Mixture-of-Experts language model with 23 billion active parameters per token, a 1M-token context window, and an Apache 2.0 license…

23:09
2026-10-15
huggingface.co
large-language-models

PrismML Releases Bonsai 2 2B, 4B, and 9B

PrismML released Bonsai 2 in 2B, 4B, and 9B parameter sizes, publishing the models on Hugging Face as GGUF and MLX 2-bit quantized builds under the prism-ml organization. The Ternary-Bonsai-2-9B-gguf …

21:41
2026-10-15
huggingface.co
artificial-intelligence

Show HN: An improved kokoro distillation in 9MB

Full-stack developer MithrilMan released an improved distillation of the Kokoro text-to-speech model at roughly 9MB with about 25x real-time factor, publishing the Apache-2.0 code on GitHub and weight…

20:34
2026-10-15
huggingface.co
large-language-models

Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

IBM released Granite Switch 4.1, with Granite-Switch-4.1-8B and -30B models that combine a Decision aLoRA, a Guardian aLoRA, and the Granite-Speech-5.0-Turbo-CTC ASR model into a single hosted endpoin…

15:31
2026-10-15
huggingface.co
machine-learning

Finding overflow and NaN edge cases in numerical code: numguard

Bhaskar Gurram released numguard, an open-source tool that tests numerical array code for edge cases including NaN, ±inf, overflow, subnormals, cancellation and float16/32/64 precision, comparing resu…

09:08
2026-10-15
huggingface.co
artificial-intelligence

Apertus 1.5 Release Notes

Swiss AI released the Apertus 1.5 8B and 70B model weights on Hugging Face on July 24, 2026 under an Apache 2.0 license, adding 4 trillion tokens of text and multimodal training data to the 8B model a…

00:00
2026-10-15
huggingface.co
generative-ai

Welcome FLUX.3 Image Klein in Diffusers

Black Forest Labs released FLUX.3 Image Klein, an open image generation model that runs in Hugging Face Diffusers from day one and handles text-to-image, multi-reference image-to-image, and bounding-b…

22:37
2026-10-14
huggingface.co
ai-safety

Local AI - How do you choose your models

A non-technical user named Tim described a 21-question, seven-step honesty test he runs against local AI models to check whether they admit missing information instead of fabricating it. The seven ste…

15:03
2026-10-14
huggingface.co
ai-agents

How to keep what the model makes up out of the agent

A new agent architecture separates model reasoning from execution by requiring that every value an agent acts on be traced to a declared source — what the user said, settings the user approved in adva…

17:05
2026-10-13
huggingface.co
large-language-models

Run fast, private agents on-device with LFM2.5-24B-A2B

LiquidAI released LFM2.5-24B-A2B, a 24B-parameter reasoning model with 2B active parameters per token, built for on-device agent workloads. The model scores 48.09 on LiveClaw versus 38.19 for Qwen3.6-…

19:17
2026-10-12
huggingface.co
ai-infrastructure

Sanity check on my hybrid RAG settings

A developer running a hybrid RAG stack of FastAPI, ChromaDB, PostgreSQL full-text search, Redis and BAAI/bge-reranker-base asked for a review of retrieval settings including a 0.3 similarity threshold…

← prev page 18 / 71 next →