Review or Reviews

테크, 개발, AI, 하드웨어 — 실사용 기반 리뷰와 가이드

최신 글

더 보기

The Open-Model Cost Chart Everyone's Sharing Is API Prices. Here's What Self-Hosting Actually Gets You (Measured)

The intelligence-vs-cost chart making the rounds shows open models winning the value quadrant. True, but the x-axis is API token price. The cheap open winners are 100B-to-1T MoEs you can't run on a desktop GPU. Here's what you can actually self-host on an 11GB and a 24GB card, measured, and where the real ceiling is.

6/23

I Added a Verify Layer to My Local RAG to Catch Hallucinations. It Caught Me Being Wrong Twice About My Own Corpus

A claim-verification layer for a local RAG co-scientist, inspired by Karpathy's llm-wiki pattern. I tried to measure whether it catches hallucinations, almost shipped a false finding, and ended up with a clearer picture of what claim-checking can and can't do: it reliably catches values that are absent from the context, misses a real number pinned to the wrong question, and misses a false premise outright, and a model can't reliably referee its own blind spots.

6/19

What Actually Runs Well on a GTX 1080 Ti in 2026 (Measured)

The 'GPU poor' narrative says 24GB-and-below cards are eating well now thanks to QAT and MTP. But what about an 8-year-old 11GB GTX 1080 Ti? I measured it: Gemma 4 12B QAT at ~32 tok/s, Qwen3 8B at ~46, all fully on the GPU. Here's the table and where the ceiling is.

6/12

MTP Isn't Always a Win: 1.95× on My 3090, but Speculative Decoding Is Hardware-Dependent

MTP gave Gemma 4 12B QAT a 1.95x generation speedup on my 3090. But the same model with the same MTP draft runs 0.87x — slower — on an M1 Max. Speculative decoding is a hardware-dependent lever, not a free switch. Here are the measured numbers and why the draft-to-verify ratio decides it.

6/11

Gemma 4 QAT on a 1080 Ti: What 'Quantization-Aware' Actually Buys — and Fitting the 12B on 8 GB at 16k

QAT is the buzz around Gemma 4, so I ran it on actual old hardware. The quality claim holds up (vs naive Q4), the speed win is modest (~9%), and yes — you can run the 12B on an 8 GB card at 16k context. Here are the measured numbers and the exact recipe.

6/10

The Prefill Wall: Why MTP's 2× Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

My last post doubled generation with MTP. A reader asked the question I'd skipped — what about prompt processing at long context? I measured prefill across context sizes on a 3090: a 64k prompt takes ~59s before the first token, and MTP can't touch that. Here's the math on when MTP's 2× actually matters, and when prefill swallows it.

6/10