Machine
RX 9070 Xt · Ryzen 5 9600X #a9b9839e
6 runs of 5 models since Nov 17, 2026. Last run Nov 17, 2026.
6
runs
5
models
5
configs
1
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 9070 XT 16 GB
- CPU
- AMD Ryzen 5 9600X 6-Core Processor 6 cores
- RAM
- 31 GB
- OS
- Windows 11 Pro 26H2
- Tools
- llama.cpp 6
- Client
- 0.4.99
Models on this machine
One dot per model, at its best config. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Best trade-off: quality 60+, and nothing else here is both faster and betterOther models · dot size = number of runs
Medians of each model's best config, 5 models.
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
swift-1.5-iq2_xs
1 run · 1 config
tiel-coder-35b-a3b-ud-q4_k_xl
1 run · 1 config
ornith-1.5-35b-a3b-apex-i-quality
2 runs · 1 config
★ bestllama.cpp64k ctxthinking on
×2 runs
86.284.0–88.4
steady
22.1 tok/s
18.8–25.5
ornith-1.5-35b-a3b-apex-i-mini
1 run · 1 config
qwen3.8-flash-next-coder-iq1_m
1 run · 1 config
Compare with another machine
Run history
Nov 17, 2026
22:47tiel-coder-35b-a3b-ud-q4_k_xlllama.cpp20.0 tok/s86.322:24ornith-1.5-35b-a3b-apex-i-minillama.cpp82.4 tok/s84.518:25ornith-1.5-35b-a3b-apex-i-qualityllama.cpp25.5 tok/s88.417:51swift-1.5-iq2_xsllama.cpp25.2 tok/s86.806:54qwen3.8-flash-next-coder-iq1_mllama.cpp25.6 tok/s76.604:12ornith-1.5-35b-a3b-apex-i-qualityllama.cpp18.8 tok/s84.0