23:54
Gemma 4 26B A4B vs Qwen3.5 35B A3B: MoE Models Battle Locally
Fahd Mirza runs a direct head-to-head comparison of two mixture-of-experts models — Gemma 4 26B A4B (activating 3.8 billion parameter...
Sort by: Newest Items
There are 104 items in this page
23:13
Gemma-4 31B vs Qwen3.5 27B: Hands-on Local Comparison of Two Top Dense Models
Fahd Mirza pits two of the strongest open-weight dense models against each other in a live local benchmark: Google DeepMind's Gemma 4...
16:57
Gemma-4 26B A4B + vLLM: Best MoE Model of 2026: Running Locally
Fahd Mirza puts Google's Gemma-4 26B A4B through its paces locally, starting with a clear explanation of what the model name actually...
13:21
Gemma 4 E2B + Hermes Agent + vLLM: Multimodal AI Stack Locally for Free
Fahd Mirza demonstrates a full local stack for running Google's Gemma 4 E2B instruction-tuned model through the Hermes agentic framew...
08:33
Qwen3 Speculator Eagle: Red Hat Made Qwen3-8B 6x Faster: Full Hands-on Guide
Red Hat has quietly entered the AI inference space with a significant technical contribution: a speculative decoding model that makes...
09:20
Run Dots.mOCR Locally — OCR, LaTeX, SVG From Any Image
dots.m OCR is a 1.7-billion-parameter vision-language model from Red Note — the Chinese lifestyle platform also known as Little Red B...
08:53
NVIDIA NemoClaw + OpenShell: OpenClaw Agent in a Secure Sandbox – Local vLLM Setup
At GTC 2026, NVIDIA announced NemoClaw — an official security and sandboxing layer for OpenClaw agents, built in collaboration with O...
10:33
OmniCoder-9B Running Locally: I Tried to Break It With Real Engineering Tasks
Fahd Mirza puts OmniCoder-9B — a coding-focused model from Tesslr, fine-tuned on the Qwen3.5 9B hybrid architecture — through a hands...
13:48
Qwen3.5 9B at 4-Bit: Intel’s Quantized Model Runs Locally with 4x Less VRAM
Fahd Mirza demonstrates running Intel's Auto Round INT4 quantized version of Qwen 3.5 9B locally using vLLM, covering both the practi...
12:01
Microsoft Phi-4-Reasoning-Vision-15B: Run Smart Multimodal Model Locally
Microsoft's Phi-4-Reasoning-Vision is a newly released 15-billion-parameter open-weight multimodal model built for two focused tasks:...