Machine
2× Gtx 1070 · Core i7-9700KF #1e23084c
8 runs of 3 models since Nov 18, 2026. Last run Nov 20, 2026.
8
runs
3
models
5
configs
2
configs run 2+ times
Hardware
- GPU
- 2× NVIDIA GeForce GTX 1070 16 GB
- CPU
- Intel(R) Core(TM) i7-9700KF CPU @ 3.60GHz 8 cores
- RAM
- 11 GB
- OS
- Debian GNU/Linux 13 (trixie)
- Tools
- llama.cpp 8
- Client
- 0.4.99
Best config per model
sort
Runs with the same model, quant, tool, context, thinking and KV cache count as one config. Numbers are the median of its runs, and each dot is one run on the 0–100 quality scale. ★ marks the best config with at least 2 rated runs.
configrunsqualityeach runspeed
Huihui-Ornith-1.5-35B-A3B-abliterated-PXQN3
2 runs · 1 config
★ bestllama.cpp64k ctxthinking on
×2 runs
83.480.3–86.5
steady
20.4 tok/s
20.4–20.5
occamy-1.0-abliterated-PXQN3
4 runs · 2 configs
★ bestllama.cpp64k ctxthinking on
×3 runs
82.980.8–84.0
steady1 slow run
19.5 tok/s
12.4–23.9
Huihui-Qwen3.6-35B-A3B-abliterated-ggml-model-PXQN3
2 runs · 2 configs