08:39
Why You Shouldn’t Run Qwen3.8 2.4T Locally
Fahd Mirza delivers a frank assessment of Qwen's newly released Qwen3 2.4-trillion-parameter open-weight model, making the case that...
Sort by: Newest Items
There are 104 items in this page
10:42
NeMo Switchyard: NVIDIA’s Model Router, Tested Locally
Fahd Mirza installs and demonstrates NeMo Switchyard, a newly released NVIDIA tool written in Rust that acts as an intelligent model...
12:51
Nemotron 3.5 Lightning: Specialized Local AI for Long-Running Agents
Fahd Mirza walks through a complete local installation and live test of NVIDIA's newly released Nemotron 3.5 Lightning — a 30-billion...
11:55
Run Muse Glimmer 30B Locally: Open Agentic Model
Fahd Mirza walks through installing and testing Muse Glimmer 30B — described as Meta's first open-weights release from its superintel...
19:50
Taking Reinforcement Learning Cross Datacenter — Nan Jiang, Modal
At an AI Engineer conference, Nan Jiang from Modal presents a technical architecture for running reinforcement learning post-training...
46:18
How Open Source Became AI’s Backbone | Inferact with a16z
In this a16z-hosted conversation, Simon Mo — co-founder of Infact and lead maintainer of vLLM, the open-source inference engine now r...
09:48
Mistral Shieldstral, Content Moderation Changed in Plain English
Fahd Mirza walks through a local installation and live evaluation of Mistral's newly released Shieldstral — a 3-billion-parameter ope...
01:42:54
The Inference Frontier: 10x Faster Models to Self-Optimizing AI — Philip Kiely & Ali Taha, Baseten
The Latent Space podcast sits down with Philip Kiely and Ali Taha from Baseten to walk through the full lifecycle of a production inf...
12:23
Microsoft Fara1.5 27B: Local Install + Real Browser Automation Demo
Fahd Mirza installs and live-tests Microsoft's newly released Fara 1.5 27B, a vision-only browser automation model that controls a we...
08:12
How to Run Kimi K3 Locally (3 Ways)
Fahd Mirza delivers an honest, hardware-grounded assessment of running Kimi K3 — Moonshot AI's 2.8-trillion-parameter, 104-billion-ac...