2 builds of Huihui-Qwen3.8-27B-abliterated-GGUF, 2 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.
trained 256K · proved 128K context, by huihui-ai Q4_K_S
13.2 tok/s peak, by huihui-ai Q4_K_S
What it fits on
The smallest build needs about 28.0 GB; 3 of 18 kinds of machine on the network can hold it. Bars: each kind's memory (its card's, else RAM) · ticks: every build, at the size it held plus a fifth for the prompt.
Carbon per million tokens
Lowest build on each machine · 1 of 1 read off a power sensor, the rest modelled from the parts · fewer grams is better
Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (EU grid average (applied to NL); Ember Global Electricity Review 2025 (2024 generation), location-based). Facility overhead is not included. A machine on its own solar is not credited until it can prove it.
Measured by
The people whose machines signed these numbers
proved by at least one build: Tool calling · Structured output · Sustained output · Extended thinking · Vision · Counts in images · Multiple images at once · Spatial reasoning · Writes code · Reasons about code · Synthesises sources · Follows instructions
Each its own file with its own page: the machines that ran it and their signatures.
| build | engine | whose work | memory | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|
| Q4_K_S by huihui-aihf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_Ssafety removed | ollama | derivative · huihui-ai | 28.0 GB | 128K | 13.2 | 1 |
| Q4_K_M by huihui-aihf.co/huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:Q4_K_Msafety removed | ollama | derivative · huihui-ai | 29.0 GB | 128K | 10.0 | 1 |