08:57
Google Releases Gemma 4 MTP Drafters – Run Locally and DFlash Comparison
Fahd Mirza demonstrates Google's newly released MTP (multi-token prediction) draft models for the Gemma 4 family, running live tests...
Sort by: Newest Items
There are 90 items in this page
08:44
Are AI Coding Skills Just Hype? I Tested Them
Web Dev Cody tackles a question most developers using agentic coding tools have avoided: do AI \"skills\" — instructional prompt file...
11:03
I Didn’t Expect This: Opus 4.7 vs GPT 5.5
Web Dev Cody runs a structured head-to-head comparison of Claude Opus 4.7 (via Claude Code) against GPT-5.5 (via OpenAI Codex) across...
12:24
Mistral Medium 3.5 128B: Built for Long Stretches on Coding: Full Testing
Fahd Mirza puts Mistral Medium 3.5 through hands-on testing in this evaluation of the newly released 128-billion-parameter dense mode...
32:34
GPT-5.5 vs Claude vs Gemini: The Real Difference Nobody’s Talking About
Nate B Jones of AI News & Strategy Daily takes GPT-5.5 through three demanding real-world evaluations — an executive knowledge-work p...
40:52
Hermes Agent is INSANE…
Wes Roth builds and runs a custom model benchmark using a physics-based gravity well ship simulation — a game where AI models must it...
40:13
6 Chinese AI Models Compared – DeepSeek vs Kimi vs GLM vs Qwen vs MiniMax vs MiMo
Fahd Mirza runs a no-retries, same-prompt coding benchmark across six of China's most capable AI models: DeepSeek V4 Pro, Kimi K2.6 (...
20:24
What Do Models Still Suck At? – Peter Gostev, Arena.ai, BullshitBench
In this conference talk, Peter Gostev — head of AI at Moonpig and contributor to Arena.ai — makes the case that benchmark leaderboard...
17:17
Nano Banana Finally Dethroned. GPT-Image 2.0 FULLY tested
Futurepedia's creator runs an extensive hands-on evaluation of OpenAI's GPT-Image-2 (ChatGPT Images 2.0), testing it head-to-head aga...
39:04
My M5 Max, Gemma 4, MLX LOCAL Stack. (This KILLS MODEL PROVIDERS)
IndyDevDan runs a structured head-to-head benchmark between a fully specced Apple M5 Max MacBook Pro and its M4 Max predecessor, test...
18:13
Comparing Full Precision vs Ollama Version of Qwen3.6-35B-A3B Locally
Fahd Mirza runs a direct head-to-head comparison of Qwen 3.6 35B-A3B (a 35-billion-parameter mixture-of-experts model) in two configu...
38:54
Claude Code + Opus 4.7 = Ultimate Coding Agent
David Ondrej spent four hours testing Claude Opus 4.7 immediately after launch and combined hands-on evaluation with a detailed read-...
16:34
Is ERNIE Image Turbo Better Than FLUX? I Tested It Locally
Fahd Mirza installs and tests Baidu's ERNIE Image Turbo locally, an open-weights text-to-image model built on a single-stream diffusi...
10:16
Running LLMs locally: Practical LLM Performance on DGX Spark — Mozhgan Kabiri chimeh, NVIDIA
Mozhgan Kabiri chimeh, Developer Relations Manager at NVIDIA, presents empirical benchmarking results from running large language mod...
12:10
New Tests Reveal The Truth About China’s AI Progress…
TheAIGRID examines new benchmark data challenging the prevailing narrative that Chinese AI labs have caught up with Western frontier...
12:07
The Most “Weird” LoRA for LTX 2.3? I Found the Truth| 3 Camera Angles to Test the Galaxy ACE LoRA
Galaxy ACE is a LoRA (Low-Rank Adaptation) built for the LTX 2.3 video generation model that simulates the visual aesthetic of a low-...