12:14
Ternary Bonsai 27B: Full Model, 2-Bit, Run on Phone or Laptop or GPU
Fahd Mirza runs Bonsai 27B — a 27-billion parameter open-weight model from Prism ML based on Gemma 3 27B — on an NVIDIA RTX A6000 GPU...
Sort by: Newest Items
There are 33 items in this page
13:00
Tess-4-27B + EAGLE-3: Local Reasoning, Nearly 2× Faster
Fahd Mirza demonstrates running Tess-4-27B — a reasoning-capable fine-tune of Qwen 3.6 27B by Miguel de Icaza — locally on an NVIDIA...
08:51
Qwen3.6-27B with Thinking Cap on: Same Accuracy, 36% Less Thinking
Fahd Mirza runs a live, unscripted comparison between Qwen3.6-27B and a community fine-tune called Thinking Cap — a variant of the sa...
13:29
Control What Your AI Agents Can Do: Archestra + Ollama Hands-On
Fahd Mirza walks through Orchestra (stylized as Archestra), an open-source platform built for running AI agents safely in production,...
08:09
Someone Fine-Tuned a Model on 10 Examples in 3 Minutes: Qwable-5 27B Coder
Fahd Mirza uses a deliberately provocative model release — Qwable-5 27B Coder — as the centerpiece of a broader argument about credib...
14:42
Qwen3.6 27B (Pi-Reasoning GGUF) – Fine-Tuned for Local Heavy AI Agent
Fahd Mirza tests Pi-Reasoning, a community fine-tune of Qwen 3.6 27B built specifically for agentic coding — tasks like reading files...
09:40
DFlash Just Got Faster: 4x Speed with 160 tok/s Locally
Fahd Mirza benchmarks DFlash with SGLang's new SpecV2 overlapping scheduler on an NVIDIA H100 80GB GPU, demonstrating a 4.3x throughp...
13:26
Gemma4 12B vs Qwen3.6 27B — The Veteran vs The Newcomer
Fahd Mirza runs a structured head-to-head comparison of Gemma 4 12B and Qwen 3.6 27B on the same Nvidia H100 80GB VRAM system, testin...
32:57
Unsloth Studio is insane… fine-tune any AI model locally
Unsloth Studio is a free, open-source desktop application that brings LLM fine-tuning to consumer hardware — and this video by David...
10:06
DFlash Leaves Qwen Territory – Gemma 4 31B Now Runs 5x Faster with Speculative Decoding
Fahd Mirza demonstrates the first end-to-end deployment of Llama Box DFlash with Google's Gemma 4 31B model, following the merge of P...