Artificial Intelligence
Explore practical insights, research, and benchmarks on artificial intelligence, including generative AI, large language models, RAG, governance frameworks, MLOps practices, and AI hardware. Gain an understanding of key tools, implementation strategies, and enterprise use cases shaping the AI landscape.
Explore Artificial Intelligence
- LLMInsightSep 21
LLM VRAM Calculator for Self-Hosting
Self-hosting an LLM means running inference on hardware the operator controls rather than via a third-party API, which changes the cost, data control, and privacy profile. Whether a model runs at all depends on memory. The calculator estimates the VRAM or unified memory a model needs to run locally, based on the model, its precision,…
- AI HardwareBenchmarkSep 21
Multi-GPU Benchmark: B200 vs H200 vs H100 vs MI300X
For over two decades, optimizing compute performance has been a cornerstone of my work. We benchmarked NVIDIA’s B200, H200, H100, and AMD’s MI300X to assess how well they scale for Large Language Model (LLM) inference. Using the vLLM framework with the meta-llama/Llama-3.1-8B-Instruct model, we ran tests on 1, 2, 4, and 8 GPUs. We analyzed…
- AI HardwareBenchmarkSep 21
GPU Concurrency Benchmark: H100 vs H200 vs B200 vs MI300X
I have spent the last 20 years focusing on system-level computational performance optimization. We benchmarked the latest NVIDIA GPUs, including the NVIDIA’s H100, H200, and B200, and AMD’s MI300X, for concurrency scaling analysis. Using the vLLM framework with the gpt-oss-20b model, we tested how these GPUs handle concurrent requests, from 1 to 512. By measuring…
- LLMBenchmarkSep 18
Agentic IT: Can AI Agents Design a Benchmark
We tested 16 models on a benchmark design in text-to-SQL and tool calling. Each model built one benchmark per topic, for a total of 32 submissions. No submission passed every rubric criterion. The agents could build and run tests, but none demonstrated both a blank-answer test and a correct-answer test of their own scorer. Text-to-SQL…
- LLMBenchmarkSep 17
AIM Enterprise: Agentic Enterprise Benchmark
Enterprises use LLMs every day for their regular tasks. To find the most cost-efficient LLMs, we designed AIM Enterprise, an agentic enterprise benchmark, where we used 69 real enterprise tasks across strategy, marketing, HR, sales, and operations. Two judge models scored every file that passed the checks. On 32.7% of the individual scores the two…
- AI HardwareBenchmarkSep 17
DGX Spark alternatives: RTX, Ryzen AI Halo and Mac Studio
We compare published DGX Spark, RTX and Ryzen AI Halo inference benchmarks, covering prompt processing, token generation and longer contexts. Alternatives include Framework Desktop, Mac Studio and GB10 systems from other manufacturers. Decode speed measures output tokens generated per second. Higher values mean faster response generation. All six results use GPT-OSS 20B MXFP4 in Ollama…
- AI HardwareOpen World EvaluationSep 16
Free Cloud GPUs: Models, Limits and Access Requirements
Free cloud GPUs are available through Python notebooks, AI demos and monthly compute credits. Compare GPU hardware, free allowances and access requirements, or check which services suit your workload. Two T4s provide two separate 16 GB memory allocations. Running a model across both requires software that distributes the workload. The combined capacity does not make…
- ChatbotsInsightSep 15
Wu Dao 3.0: China's Version of GPT-5
When the US cut off China’s access to advanced chips, the Beijing Academy of Artificial Intelligence faced a choice: complain about restrictions or work around them. They picked the second option. Wu Dao 3.0, launched in July 2023, throws out the playbook. No massive trillion-parameter models competing for headlines. Instead, BAAI now builds compact models…