Machine
RTX 4090 D · Core Ultra 7 270K Plus #0c0d6dd0
3 runs of 2 models since Oct 30, 2026. Last run Oct 30, 2026.
3
runs
2
models
2
configs
1
configs run 2+ times
Hardware
- GPU
- NVIDIA GeForce RTX 4090 D 24 GB
- CPU
- Intel(R) Core(TM) Ultra 7 270K Plus 24 cores
- RAM
- 63 GB
- OS
- Windows 11 Pro 25H2
- Tools
- llama.cpp 3
- Client
- 0.4.98
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
Qwen3.8-27b-iq3s
1 run · 1 config
Qwen3.8-27b-q4s
2 runs · 1 config
★ bestllama.cpp200k ctxthinking oneffort medium
×2 runs
83.176.6–89.6
varies
65.7 tok/s
64.2–67.3