Build Logs

7 articles

Qwen-Image-2.1 on a 32GB Mac: The Biggest GGUF Is the Fastest
14 min read

Qwen-Image-2.1 on a 32GB Mac: The Biggest GGUF Is the Fastest

Qwen-Image-2.1 cut its image generator from 20.4B to 7B parameters. Measured at four quantizations on an Apple M5 32GB: Q8_0 is the fastest and the most faithful, native transparency works only at enough steps, and the license restricts the model but says nothing plain about your images.

Build Logs
Quantizing the KV Cache Made It Faster, Not Just Smaller
11 min read

Quantizing the KV Cache Made It Faster, Not Just Smaller

The usual framing is memory for quality. Measured across three configurations on one Apple M5 32GB, an 8-bit KV cache cut memory 36% at 64K and raised generation speed 52% — and across every output compared, it did not change what the models wrote.

Build Logs
Long Context on a 32GB Mac: Four Local LLMs, Measured to 128K
19 min read

Long Context on a 32GB Mac: Four Local LLMs, Measured to 128K

Four local models measured at 4K to 128K context on one Apple M5 32GB. Two of them are the same size; at 64K one runs 3.3x faster on half the memory. At 128K a 12B model holds the window in the same memory as a 3B one, and faster. The difference is sliding-window attention.

Build Logs
Running TRELLIS.2 on a Mac (3/3): The Optimizations That Actually Won
18 min read

Running TRELLIS.2 on a Mac (3/3): The Optimizations That Actually Won

The optimizations that survived measurement: load time cut 5x, mesh extraction 67x, and a sixth twist that overturned my own conclusion about MPS attention.

Build Logs
Running TRELLIS.2 on a Mac (2/3): Five Bottlenecks I Guessed Wrong
9 min read

Running TRELLIS.2 on a Mac (2/3): Five Bottlenecks I Guessed Wrong

Five confident guesses about where the Apple Silicon port was slow — and how honest measurement killed every one, plus the profiling methodology that made the numbers trustworthy.

Build Logs
Running TRELLIS.2 on a Mac (1/3): Porting a CUDA-Only Image-to-3D Model to Apple Silicon
7 min read

Running TRELLIS.2 on a Mac (1/3): Porting a CUDA-Only Image-to-3D Model to Apple Silicon

How I got Microsoft's CUDA-only image-to-3D model (TRELLIS.2) to run on Apple Silicon: an idempotent patcher, swapping the CUDA kernels out one by one, and the first generation.

Build Logs
One Session with Claude Fable 5 Un-Stuck My Abandoned Three.js Game
7 min read

One Session with Claude Fable 5 Un-Stuck My Abandoned Three.js Game

My son-inspired Three.js endless runner sat abandoned for nine months: no physics, horror-movie visuals, no real gameplay. One session with Claude Fable 5 produced 48 commits and solved exactly the systems that had me stuck — then export controls took the model offline that same day.

Build Logs