Skip to content
@www-ai-rs

ai.rs

Custom AI assistants for e-commerce. Fine-tuned open-source LLMs (Qwen, Llama, Mistral) with RAG pipelines. Product recommendations, sales automation, pricing.

ai.rs

Custom AI for e-commerce — and a publication about running large language models on hardware you own.

We build AI sales assistants that know your products, pricing, and inventory in real time. We also measure things and publish the numbers, including the ones that don't flatter the hardware.

🌐 ai.rs · 📧 github@ai.rs · 📍 Belgrade, Serbia


What we publish

Everything below is measured on our own hardware, with the methodology in the article.

Local hardware and inference

DeepSeek-V4-Flash on Two GB10s 304B params, 1M context, 88 tok/s on 83 W — and a CUDA kernel it got wrong
Self-Hosted Claude Code: What Each Memory Tier Buys 32 GB, 128 GB, 256 GB — what each actually runs
RTX 5090 vs GB10 (HP ZGX) 32 GB at 1.8 TB/s against 128 GB at 273 GB/s
Will This LLM Fit My GPU? The VRAM formula, and a one-command check
4-Bit Quantization Decoded INT4 QAT, MXFP4, NVFP4 — what the formats actually change

Running models locally

Qwen 3.6 27B: a Local Coding Model You Can Actually Run Single 4090, within 4 points of Opus 4.6 on SWE-bench
Qwen3-Coder 30B-A3B on RTX 5090 with Ollama 231 tok/s, 64K context, full setup log
Gemma 4 LoRA Fine-Tuning on RTX 5090 What works, what doesn't
Synthetic Data for Fine-Tuning Generating your own training set

How it actually works

Mixture of Experts, Explained Why 304B params can activate 13B per token
The KV Cache The trick that makes LLMs fast, then slow
Prompt Processing vs Token Generation Two speeds, and why one number misleads
What a 256K (or 1M) Context Window Costs Memory, compute, and bandwidth per token
What is RAG and Why Your AI Needs It Retrieval, grounded in a real use case
LLM Post-Training Explained SFT, DPO, and GRPO

Models and comparisons

Gemma 4 vs Qwen 3.5 vs Llama 4 Updated benchmarks
Kimi K2.6 Explained A trillion-parameter open model, and its memory bill
Claude Opus 5: What's New What changed, and whether to switch
BM25 vs Embeddings Why keyword search still wins for product search
LLM Security: From 17% to 94% Attack Resistance Prompt injection, measured before and after

New to this? The site has a beginner track with no code and no jargon.


Repositories

  • gb10-deepseek-v4-flash — two-node DGX Spark operator tooling and measurement harness for DeepSeek-V4-Flash: launch and status scripts, 2 Hz GPU-rail power sampling, and a harness that executes generated code against hidden tests.

What we do commercially

  • LLM fine-tuning — custom-trained open models on your product catalog
  • RAG pipelines — live retrieval from your database for accurate pricing and availability
  • AI sales assistants — embedded chat that recommends products and answers questions
  • Dedicated deployment — your own server, your own data, no shared infrastructure

Stack: fine-tuned open-weight LLMs (Qwen, Gemma, Llama, DeepSeek), custom RAG with vector search plus live database queries, Rust and Python infrastructure, on-premise or dedicated cloud.

Serving e-commerce businesses across Europe and beyond.

Popular repositories Loading

  1. .github .github Public

    Organization profile and README

  2. gb10-deepseek-v4-flash gb10-deepseek-v4-flash Public

    Two-node DGX Spark operator tooling and measurement harness for DeepSeek-V4-Flash

    Python

Repositories

Showing 2 of 2 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…