Machine
RTX 4070 Ti Super · Ryzen 7 9700X #ba7805c4
24 runs of 20 models since Jul 25, 2026. Last run Aug 15, 2026.
24
runs
20
models
24
configs
0
configs run 2+ times
Hardware
- GPU
- NVIDIA GeForce RTX 4070 Ti SUPER 15 GB
- CPU
- AMD Ryzen 7 9700X 8-Core Processor 8 cores
- RAM
- 61 GB
- OS
- Windows 11 Professionnel 25H2
- Tools
- LM Studio 24
- Client
- 0.4.36
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, 17 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-1.0-35b
1 run · 1 config
unsloth/ornith-1.0-9b
1 run · 1 config
ornith-1.0-9b
2 runs · 2 configs
google/gemma-4-12b
1 run · 1 config
qwen/qwen3.5-9b
1 run · 1 config
unsloth/gemma-4-12b-it-qat
1 run · 1 config
gpt-oss-20b
1 run · 1 config
openai/gpt-oss-20b
1 run · 1 config
laguna-xs-2.1
2 runs · 2 configs
google/gemma-4-12b-qat
1 run · 1 config
Compare with another machine
Run history
Aug 9, 2026
08:07bonsai-27bLM Studio83.7 tok/s67.0Jul 26, 2026
19:48gpt-oss-20bLM Studio148 tok/s70.519:36glm-4.6v-flashLM Studio54.5 tok/s65.918:59qwen3.5-9bLM Studio62.7 tok/s72.918:47gpt-oss-20bLM Studio155 tok/s71.218:38ornith-1.0-9bLM Studio62.4 tok/s73.518:29nanbeige4.1-3bLM Studio73.3 tok/s60.418:12ornith-1.0-9bLM Studio62.5 tok/s73.317:58gemma-4-12b-it-qatLM Studio67.2 tok/s71.617:43gemma-4-26b-a4b-it-qatLM Studio48.4 tok/s68.810:43qwen3.6-28b-reap20-a3bLM Studio44.3 tok/s57.810:35qwen3.6-14b-a3b-fablevibesLM Studio45.2 tok/s58.610:25glm-4.7-flash-reap-23b-a3bLM Studio40.9 tok/s16.210:00gemma-4-26b-a4b-qatLM Studio51.4 tok/s68.809:25gemma-4-12b-qatLM Studio65.9 tok/s69.209:17gemma-4-12bLM Studio24.9 tok/s73.3