← Back to the full write-up on hijoseromero.com
Qwen 3.8-27B (the new challenger) vs Qwen 3.6-35B-A3B (the reigning champ). Full precision, thinking off, tools off, one shot each. Claude Opus 4.6 rides along as the cloud wildcard, not a contestant.
| Qwen 3.8-27B | Qwen 3.6-35B | Opus 4.6 (wildcard) | |
|---|---|---|---|
| File on disk | 54.7 GB | 71.1 GB | cloud |
| Architecture | 27B dense | 35B MoE, ~3B active | frontier |
| Generation speed | ~8.8 tok/s | ~27 tok/s | ~70 tok/s |
| Whole exam took | ~58 min | ~14 min | ~40 min (max effort) |
| Peak memory | 71 GB | 77 GB | n/a |
| Can see images | YES | no | yes |
| Cost to run the exam | electricity | electricity | $7.13 |
| The rig they ran on | GMKtec EVO-X2, Ryzen AI Max+ 395, 128 GB unified memory | Anthropic's cloud | |
Every single token requires reading ALL of the model's active weights from memory. The dense 27B at BF16 reads ~55 GB per token; at ~256 GB/s of memory bandwidth that caps out near 5-9 tok/s no matter how much total RAM there is. The 3.6 MoE is faster despite the bigger file because only ~3B parameters are active per token (~7 GB read). More memory makes models FIT. Bandwidth makes them FAST. Quantization attacks exactly this: the quant-ladder results page runs this same exam at every quant level, and the thinking-dial page runs it at every reasoning level.
| The raw per-run metrics | Qwen 3.8 · Qwen 3.6 · Opus 4.6 |
| The exact prompts, as plain text | Blockfall · Eruption · The Ledger · Blind Artist |
These are affiliate links. If you buy through them I may earn a small commission at no extra cost to you. As an Amazon Associate I earn from qualifying purchases.