13:19
Kimi K2.7 Code + Hermes Agent – Clinically Certified to Be Insane
Fahd Mirza puts Kimi K2.7 Code — Moonshot AI's latest open-weight coding model — through a demanding real-world test using the Hermes...
Sort by: Newest Items
There are 126 items in this page
12:04
NVIDIA Ships Nemotron 3.5 ASR Streaming 0.6b: Run Locally on CPU
Fahd Mirza provides a hands-on walkthrough of NVIDIA's newly released NeMo-Tron 3.5 ASR — a 600-million-parameter streaming speech re...
09:42
Luce Spark: Run a 35B Model Under 16GB VRAM Locally
Fahd Mirza demonstrates LuceSpark, a memory management technique that allows a 35-billion-parameter mixture-of-experts model to run w...
14:01
DiffusionGemma GGUF: Run Google’s Fastest Model Locally on Any GPU
Fahd Mirza demonstrates how to run DiffusionGemma — Google's new diffusion-based text generation model — locally using a quantized GG...
09:03
Gemma 4 Was Broken for Agents – Google Just Fixed It
Google's Gemma 4 12B model contained a subtle but impactful bug in its official Jinja chat template that was silently breaking multi-...
11:01
Higgs Audio v3 TTS: This Model Does Not Read, It Talks in Your Language
Fahd Mirza demonstrates Higgs Audio V3, a multilingual text-to-speech model from Boson AI, running entirely locally on an Nvidia RTX...
08:21
SimpleMem + Ollama: Local AI Memory That Actually Gets Smarter
SimpleMem is an open-source AI memory framework that challenges the conventional approach taken by tools like Mem Zero and MemoryBear...
08:56
BLS-Mini-Code-1.0: Testing Cohere’s Secret Coding Model Locally
Fahd Mirza walks through a same-day local installation and test of BLS-Mini-Code-1.0, Cohere's first dedicated coding model released...
06:49
Nanowhale-100m: Fascinating Implemention of DeepSeek-V4 Architecture
Fahd Mirza walks through Nanowhale-100M, a 110 million parameter language model built entirely from scratch—no borrowed weights—that...
08:15
MisoTTS – Most Emotive Voice Model in the World – Really?
Fahd Mirza puts MesoTTS 8B — a new open-weights text-to-speech model built on the Sesame CSM architecture — through a hands-on instal...