Machine
RX 9070 9070 Xt 9070 Gre · Ryzen 7 5700X3D #a4091942
20 runs of 5 models since Jul 29, 2026. Last run Nov 13, 2026.
20
runs
5
models
9
configs
3
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 9070/9070 XT/9070 GRE 16 GB
- CPU
- AMD Ryzen 7 5700X3D 8-Core Processor 8 cores
- RAM
- 31 GB
- OS
- EndeavourOS
- Tools
- Ollama 20
- 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
qwen3.6:27b-coding
1 run · 1 config
gemma4
12 runs · 2 configs
★ bestQ4_K_MOllama8k ctxthinking on
×10 runs
71.457.9–73.4
varies2 slow runs
132 tok/s
22.0–144
gemma4:12b
2 runs · 2 configs
gemma4:26b-a4b-it-qat
4 runs · 3 configs
★ bestQ4_0Ollama8k ctxthinking default
×2 runs
67.963.7–72.1
varies
78.6 tok/s
78.6–78.6
qwen3.5
1 run · 1 config
Compare with another machine
Run history
Nov 13, 2026
23:22gemma4:latest×9Ollama132 tok/s71.6Sep 26, 2026
03:11gemma4:latestOllama74.2 tok/s54.8Aug 2, 2026
18:07gemma4:latestOllama74.4 tok/s62.2