Machine
RX 9050 9060 Xt · Ryzen 5 7500F #f6c6b32a
11 runs of 6 models since Sep 7, 2026. Last run Sep 22, 2026.
11
runs
6
models
8
configs
2
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 9050 / 9060 XT 15 GB
- CPU
- AMD Ryzen 5 7500F 6-Core Processor 6 cores
- RAM
- 30 GB
- OS
- Arch Linux
- Tools
- LM Studio 11
- Client
- 0.4.71
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, 6 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
ornith-1.5-35b-a3b-apex-mtp-i-compact
1 run · 1 config
qwen3.8-27b-gsq-rco
1 run · 1 config
tiel-coder-35b-a3b-mtp
3 runs · 2 configs
★ bestLM Studio128k ctxthinking on
×2 runs
81.380.8–81.9
steady
100 tok/s
57.6–143
grm-3.2-sky-onyx
1 run · 1 config
nail-qwen3.6-35b-a3b
4 runs · 2 configs
★ bestLM Studio64k ctxthinking on
×3 runs
78.677.3–79.0
steady
50.7 tok/s
50.1–52.1
swift-qwen3.8-27b
1 run · 1 config
Compare with another machine
Run history
Sep 22, 2026
14:17nail-qwen3.6-35b-a3bLM Studio51.1 tok/s74.513:13ornith-1.5-35b-a3b-apex-mtp-i-compactLM Studio40.0 tok/s85.612:54tiel-coder-35b-a3b-mtpLM Studio57.6 tok/s80.806:05nail-qwen3.6-35b-a3b×3LM Studio50.7 tok/s78.6