FLE Link

FLE Link / Models

Run Kate 27B (abliterated) locally on a 12 to 32 GB GPU

Kate is Katy (Swift-1.5-Qwen3.8-27B) with the refusal direction removed from the weights, as IQ4_XS in bartowski's tensor layout with our own importance matrix, plus the public DSpine b16 draft head. Requests that only sound unsafe are no longer refused (OR-Bench hard: 88 of 100 for Katy, 1 for Kate); clearly harmful ones still are, 70 of 100.

flelink run kate-27b-dspine

What you need

One NVIDIA card from 12 GB and 24 GB of RAM, and FLE v1.3.0 (the dense engine line), which FLE Link installs for this recipe.

Measured speed

RecipeDecodeMeasured on
Kate 27B + DSpineKaty without the refusal direction142.7 tok/sfrom 20 GB up all 66 layers are on the card; memory limit simulated on a 32 GB card, FLE v1.3.0 source, Nov 2026
Kate 27B + DSpineKaty without the refusal direction37.3 tok/s16 GB, 55 of 66 layers on the card; simulated on a 32 GB card in a Ryzen 9 9950X3D with 128 GB RAM; a slower CPU will be slower
Kate 27B + DSpineKaty without the refusal direction14.1 tok/s12 GB, 37 of 66 layers; memory limited on a larger card to simulate the size

Does Kate 27B + DSpine fit my card?

Graphics32 GB RAM64 GB RAM128 GB RAM
12 GB NVIDIA cardfitsfitsfits
16 GB NVIDIA cardfitsfitsfits
24 GB NVIDIA cardfitsfitsfits
32 GB NVIDIA cardfitsfitsfits
Apple Silicon Macno engineno engineno engine
No GPUno engineno engineno engine

"no engine": this recipe needs the FLE engine, which has an NVIDIA CUDA build only. File size 16 GiB including the draft model.

The verdicts are the rule FLE Link applies before it downloads anything (the rules in full). A speed is shown only for the hardware it was measured on. A size nobody measured yet? flelink bench --task pagoda --share posts yours to the benchmarks board.

Good to know

Sources

Install FLE Link

curl -fsSL https://flelink.run/install.sh | sh

Windows: irm https://flelink.run/install.ps1 | iex. Open source, MIT. No account, no telemetry. What FLE Link does →