12GB VRAM
We published someone else's benchmark. Here's the fix.
A drafter benchmark on this site was Codacus's GTX 1060 figure. Our own 3060 numbers, why it's the CPU and not PCIe, the July audit, and what a 12 GB card should run. Plus 4090 and break-even corrections and seven Quick Hits.
Strata vs llama.cpp on a 3060: The 7x Is Real. Two Flags Halve It
Qwen3.8-Flash-Next Coder on a 12 GB RTX 3060 and 32 GB of DDR4. Strata prefills 6-7x faster than stock llama.cpp. One batch setting closes most of that.
A 27B for your 12 GB card. It lost one field.
Bonsai 2 27B fits a 12 GB card and decodes 1.8x faster than its Q4, then drops from 19 to 12 of 47 on a routing split, all of it on one field. Plus 23 used-GPU price corrections, the 3060 fair-price ladder, and eight Quick Hits.
Bonsai 2 vs Qwen3.8-27B on an RTX 3090: Speed Doubled, Scope Broke
Bonsai 2 27B, PrismML's ternary Qwen3.8, on a 3090: 1.8x the decode of Q4 from a 7.2 GB file, then 12 of 47 against 19 on a routing split. One field broke.
GTX 1650 vs RTX 3060 on a 35B MoE: What the Card Buys
A $60-class GTX 1650 4 GB runs Qwen3.6-35B-A3B at 20 tok/s on 32 GB of RAM. The RTX 3060 in the same slot does 28 at the same setting and 39 tuned. Measured.
A 177B Model on a 3060: The 32 GB Number Nobody Measured
Qwen3.8-Flash-Next on an RTX 3090 and a 3060. Stock, the 3090 matches the video's 3060. One flag buys 34 to 40 percent. A real 32 GB box: 8.7 tok/s, not 22.
A weekly email with every new guide and measured benchmark.
Subscribe — free, no spam