Unbiased Bob

Qwen 3.8 27B with 32GB of RAM, Qwen 3.8 Flash Next on UnbiasedStrata with 64GB or more. Bob-Bench Wide results, both serving configs, transcript and ad-free torrent.

816B parameters on 2× B200s ties a 27B model on Bob-Bench Wide. Play the skateboard games both models wrote. Transcript and ad-free torrent.

Strata runs a 177B Qwen MoE at ~100 tok/s on one 4090. How the expert cache works, why llama.cpp is slower, and why I won't install it. Offline fork, transcript, and ad-free torrent.

Qwen3.6 35B-A3B on budget hardware: the config, a 1070 Ti trial, and 11 BBW configurations. Transcript and ad-free torrent.

PrismML's Ternary Bonsai 2 27B against three other ways to use an 8 GB card. Transcript, configs, and an ad-free download.

Qwen3.6 35B-A3B in 8 GB of VRAM by offloading the experts to system RAM. Transcript, config, and an ad-free download.

What to actually run on a 16 GB card, entirely resident in VRAM. Transcript, config, and an ad-free download.