10:49
Ling 3.0 Flash: A Production-Scale Coding Agentic Model
Fahd Mirza tests Ling 3.0 Flash, a 124-billion-parameter mixture-of-experts model from Ant Group (Alibaba's financial subsidiary), as...
Sort by: Newest Items
There are 129 items in this page
08:05
Shrinking GLM-5.2 with Colibri to Run Locally, No GPU
Fahd Mirza demonstrates how to use Colibri, an open-source inference engine, to convert and run GLM-5.2 — a 744 billion parameter mix...
05:19
This $12 billion startup finally shipped something…
Fireship covers the debut of Inkling, the first major model release from Thinking Machines — the AI lab founded by Mira Murati after...
08:12
Gemma 4 Just Got a Massive Update (Tested Live Locally)
Fahd Mirza puts Gemma 4's latest patch update under the microscope in a live session running on an Nvidia H100 with vLLM on a fresh U...
10:07
Colibrì: Running GLM-5.2 (744B) Locally in RAM With No GPU
Fahd Mirza demonstrates running GLM 5.2 — a 744 billion parameter mixture-of-experts model from Tsinghua's KEG Lab — on a single cons...
14:30
Cactus Needle – The 26M Function Calling Model
Sam Witteveen reviews Cactus Needle, an open-source 26-million-parameter function calling model from YC-backed startup Cactus, notabl...
10:54
NVIDIA’s Audex-2B: The Tiny Model That Hears, Thinks, and Speaks
Fahd Mirza installs and tests NVIDIA's Audex 2B, a newly released 2-billion-parameter model from the Neotron family that unifies audi...
08:51
Qwen3.6-27B with Thinking Cap on: Same Accuracy, 36% Less Thinking
Fahd Mirza runs a live, unscripted comparison between Qwen3.6-27B and a community fine-tune called Thinking Cap — a variant of the sa...
29:08
Fine-Tune the biggest open-source models (even with a bad PC)
David Ondrej walks through a complete tutorial for fine-tuning Kimi K2.7, a 2.7-trillion-parameter open-source model that he position...
25:21
Deepseek drops another HUGE breakthrough
AI Search provides a structured technical breakdown of DeepSeek's DSpark system, which the team claims achieves over 6x output throug...