15:31
PFlash + Qwen3.6-27B-DFlash: 10x Faster Prefill on a Single GPU: Run Locally
Fahd Mirza builds and benchmarks PFlash, a prefill acceleration tool that dramatically reduces the blank-screen wait time when feedin...
Sort by: Newest Items
There are 17 items in this page
12:03
LTX 2.3 – Improved AI Videos & Extensions in ComfyUI!
Nerdy Rodent covers the v1.1 update to LTX 2.3, an open-source AI video model from LightTricks, and demonstrates a full video extensi...
15:26
Gemma, DeepMind’s Family of Open Models — Omar Sanseviero, Google DeepMind
Omar Sanseviero, a researcher at Google DeepMind, delivers the first public conference talk on Gemma 4 just one week after its releas...
15:26
Gemma, DeepMind’s Family of Open Models — Omar Sanseviero, Google DeepMind
Omar Sanseviero, a researcher at Google DeepMind, delivers the first public conference talk on Gemma 4 just one week after its releas...
23:47
New BEST local AI image generator is here!
The AI Search channel puts Ernie Image — a newly released open-source image generator from Baidu — head-to-head against Zage, the pre...
10:40
Intel Squeezed Gemma-4 31B into INT4 – Run It Locally with Half the Memory
Fahd Mirza demonstrates how Intel's AutoRound toolkit can quantize Google's Gemma 4 31B multimodal model from FP16 down to INT4, cutt...
05:15
Google just casually disrupted the open-source AI narrative…
Fireship's Code Report covers Google's release of Gemma 4, a large language model launched under the Apache 2.0 license — making it o...
11:54
Run GLM-5.1 Locally on CPU + GPU Easily: Step-by-Step Tutorial
Fahd Mirza demonstrates how to run GLM-5.1 — the newly open-sourced flagship agentic model from Zhipu AI's GLM team — locally on a si...
17:17
Fine-Tune Gemma-4 on Your Own Dataset Locally: Step-by-Step Tutorial
This step-by-step tutorial from Fahd Mirza covers fine-tuning Google's Gemma 4 E2B model locally on a custom dataset using Unsloth an...
09:47
Google just dropped Gemma 4… (WOAH)
Matthew Berman delivers a thorough breakdown of Google's Gemma 4 model family, covering all four released sizes: effective 2B and 4B...