Machine
Ryzen 9 9955HX3D #156e8edc
8 runs of 7 models since Aug 21, 2026. Last run Aug 21, 2026.
8
runs
7
models
8
configs
0
configs run 2+ times
Hardware
- CPU
- AMD Ryzen 9 9955HX3D 16-Core Processor 16 cores
- RAM
- 60 GB
- OS
- Debian GNU/Linux 13 (trixie)
- Tools
- LM Studio 8
- Client
- 0.4.40
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
Qwen3.8-27B-MTP-UD-Q4_K_M
1 run · 1 config
Qwen3.6:35B-A3B/MTP@196K
1 run · 1 config
Qwen3.8:27B/MTP@180K
2 runs · 2 configs
Gemma4:E4B/QAT-MTP@131K
1 run · 1 config
Gemma4:E2B/QAT-MTP@131K
1 run · 1 config
Qwen3.5:4B/MTP@262K
1 run · 1 config
Qwen3.5:2B/MTP@262K
1 run · 1 config
Compare with another machine
Run history
Aug 21, 2026
12:29Qwen3.8-27B-MTP-UD-Q4_K_MLM Studio41.1 tok/s83.510:41MTP@180KLM Studio42.2 tok/s73.310:03MTP@180KLM Studio53.0 tok/s65.309:36MTP@196KLM Studio216 tok/s80.909:35MTP@262KLM Studio199 tok/s41.009:32MTP@262KLM Studio363 tok/s22.409:30QAT-MTP@131KLM Studio260 tok/s70.209:29QAT-MTP@131KLM Studio348 tok/s65.4