08:06 Coding & Builds3 months ago Loops in Hermes Agent – Hands-on Demo with Qwen3.8 27B Fahd Mirza demonstrates the newly released `/loop` command in Hermes Agent, an open-source agentic framework that gives language mode... 0 comments 1.7K views
19:32 Tutorials3 months ago Qwen3.8-27B GGUF: Run It Local with llama.cpp, Ollama & LM Studio Fahd Mirza walks through the complete process of running Qwen3.8-27B in GGUF quantized format using three local inference tools: LM S... 0 comments 2.3K views
09:28 Tutorials3 months ago DeepSeek Harness + Ollama or Any Other Provider Locally Fahd Mirza walks through the installation and configuration of DeepSeek Harness (DSH), an open-source agent framework quietly release... 0 comments 2.1K views
20:28 Benchmarks3 months ago Muse Glimmer 30B GGUF + DFlash: 3x Faster Local Inference Fahd Mirza follows up his full-precision Muse Glimmer 30B video with a focused benchmark of the GGUF quantized version running with D... 0 comments 1.7K views
11:04 Benchmarks4 months ago Maple-Preview Tested: Ternary Weights, Better on CPU than GPU, Honest Results Fahd Mirza independently tests Maple-Preview, a 20-billion-parameter sparse mixture-of-experts model from Deep Grove (an independent... 0 comments 3.2K views
08:13 Coding & Builds4 months ago Neutrino-8B Locally: Extreme Quantization Done Right Fahd Mirza takes a close look at Neutrino-8B, a model from Fermi-on that pushes ternary quantization to its logical extreme — every w... 0 comments 2.1K views
18:30 Coding & Builds4 months ago Qwen3.6-27B Fable Fusion 711: Strongest, Smartest Fine-Tune: Tested Locally Fahd Mirza installs and thoroughly benchmarks Qwen3.6-27B Fable Fusion 711, a community fine-tune that claims to be the first model o... 0 comments 3.4K views
46:01 Deep Dives4 months ago Compression at the Edge — NVIDIA, Unsloth, HuggingFace, Ollama A conference panel titled "Compression at the Edge" brings together engineers from four of the most active organizations in local AI:... 0 comments 1.1K views
08:12 Tutorials4 months ago 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... 0 comments 3.3K views
09:16 Coding & Builds4 months ago DeepSeek V4 Flash Fully Local — 32 tok/s on a Single Chip Fahd Mirza demonstrates running DeepSeek V4 Flash, a 284-billion parameter mixture-of-experts model, entirely on a single AMD Ryzen A... 0 comments 5.3K views