Machine
RX 7900 XTX · Core Ultra 5 225F #fcd17be9
8 runs of 5 models since Nov 12, 2026. Last run Nov 17, 2026.
8
runs
5
models
5
configs
2
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 7900 XTX 24 GB
- CPU
- Intel(R) Core(TM) Ultra 5 225F 10 cores
- RAM
- 61 GB
- OS
- Ubuntu 26.04.1 LTS
- Tools
- Strata 5 · llama.cpp 3
- 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
qwen3.8-flash-next-coder-iq1_m
2 runs · 1 config
★ bestStrata64k ctxthinking defaulteffort xhigh
×2 runs
87.086.5–87.4
steady
79.3 tok/s
63.4–95.3
swift-1.5-iq3_xxs
1 run · 1 config
Qwen3.8-Flash-Next-Avalon-IQ3KS-00001-of-00033
3 runs · 1 config
★ bestllama.cpp64k ctxthinking defaulteffort xhigh
×3 runs
83.581.3–86.4
steady
72.7 tok/s
66.0–73.1
qwen3.8-flash-next-unsloth-ud-iq3_xxs
1 run · 1 config
qwen3.8-flash-next-iq3_s
1 run · 1 config