09:46 Tutorials1 month ago Run Every AI Model Your Agent Needs From One Open-Source Server (SIE) The Superlinked Inference Engine (SIE) is an Apache 2-licensed, open-source server that consolidates over 150 AI models — including e... 0 comments 1.4K views
08:32 Tutorials1 month ago Stop Using OCR – EVIE: The #1 Visual Document Retriever – Run Locally Fahd Mirza introduces Tencent's EVIE (EV Preview), a 4.5 billion parameter visual document retriever that sidesteps OCR entirely by t... 0 comments 1.1K views
11:12 Benchmarks2 months ago Qwen3.8-4B Distilled: Q4 vs Q6 vs Q8 — Which Quant Actually Wins? Fahad Mirza benchmarks the Qwen 3.8 4B distilled model — built by the Emperor team, not Alibaba — across three quantization levels (Q... 0 comments 2.9K views
11:48 Reviews & Comparisons2 months ago Ox Alpha: A Free Mystery Model With 1M Context Fahd Mirza takes a blind capability look at "Aux Alpha," a mystery model quietly available on several AI providers under a code name,... 0 comments 1.1K views
12:54 Coding & Builds2 months ago Qwen3.8-27B in 2-Bit Quant: Escha-W2 Build Locally without Loss Fahd Mirza demonstrates Escha-W2, Asha Labs' aggressively quantized version of Qwen3.8 27B, which compresses the model from 50GB at f... 0 comments 4.2K views
13:42 Reviews & Comparisons2 months ago DeepSeek V4-Flash Vision Is Out: Whale Opened Its Eyes Fahd Mirza puts DeepSeek V4 Flash Vision EXP through its paces in a hands-on review recorded on the night of its release. The experim... 0 comments 2K views
10:30 Benchmarks2 months ago Ornith-1.5-9B: Great on Paper, Struggled in My Tests Locally Fahd Mirza tests the Ornith 1.5 9B model — the smallest and densest member of the Ornith 1.5 family — on a single NVIDIA A100 with 80... 0 comments 1.6K views
11:35 Coding & Builds2 months ago Ornith 1.5 35B-A3B: Self-Improving Model Goes General-Purpose: Run Locally Fahd Mirza walks through deploying Ornith 1.5 35B-A3B — the latest release from Deep Reinforce — on a single Nvidia A100 80GB GPU usi... 0 comments 4.7K views
10:22 Coding & Builds2 months ago Qwen3.8-27B Ridge: Smarter Quantization, Full Power on 12GB Fahd Mirza reviews Ridge, an architecture-aware quantization of Qwen3.8 27B produced by the Empero team — the same group behind a pre... 0 comments 5.7K views
08:06 Coding & Builds2 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 1.6K views