Machine
RX 7900 XTX · Ryzen 7 7800X3D #4de59e37
28 runs of 11 models since Apr 18, 2026. Last run Apr 25, 2026.
28
runs
11
models
18
configs
7
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 7900 XTX 23 GB
- CPU
- AMD Ryzen 7 7800X3D 8-Core Processor 8 cores
- RAM
- 31 GB
- OS
- Windows
- Tools
- Ollama 18 · LM Studio 10
- Client
- 0.4.20
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, 10 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
5 runs · 2 configs
★ bestQ4_K_MOllama64k ctxthinking default
×3 runs
77.376.9–82.3
steady
5.3 tok/s
5.0–5.3
gemma4:31b
3 runs · 2 configs
★ bestQ4_K_MOllama16k ctxthinking default
×2 runs
76.675.9–77.3
steady
5.0 tok/s
4.5–5.5
gpt-oss:20b
1 run · 1 config
qwen/qwen3.5-35b-a3b
1 run · 1 config
ministral-3:14b
2 runs · 2 configs
glm-4.7-flash
1 run · 1 config
glm-4.7-flash-unsloth:small-hotfixed-90kHEAT
1 run · 1 config
qwen/qwen3.6-35b-a3b
4 runs · 2 configs
★ bestLM Studio16k ctxthinking default
×2 runs
66.562.3–70.7
varies
32.7 tok/s
32.4–32.9
openai/gpt-oss-20b
5 runs · 3 configs
★ bestLM Studio64k ctxthinking default
×3 runs
64.662.5–75.8
varies
110 tok/s
108–111
gemma4:26b
4 runs · 2 configs
★ bestQ4_K_MOllama32k ctxthinking default
×3 runs
64.658.2–68.4
varies
25.7 tok/s
25.6–28.6
Compare with another machine
Run history
Apr 25, 2026
18:34qwen3.6-35b-a3bLM Studio32.5 tok/s68.518:02glm-4.7-flash:latestOllama7.9 tok/s69.217:49devstral-small-2:latestOllama11.8 tok/s62.5Apr 24, 2026
13:15gemma4:26bOllama28.6 tok/s58.213:11gemma4:26bOllama31.7 tok/s64.913:07qwen3.6:latestOllama5.3 tok/s82.312:47qwen3.6:latestOllama7.2 tok/s74.912:06glm-4.7-flash-unsloth:small-hotfixed-90kHEATOllama23.3 tok/s66.911:51ministral-3:14bOllama42.7 tok/s69.211:41gemma4:31bOllama4.1 tok/s77.2Apr 22, 2026
20:29gemma4:26bOllama25.7 tok/s68.420:24ministral-3:14bOllama43.0 tok/s66.020:15gemma4:31bOllama5.5 tok/s77.319:55gpt-oss:20bOllama70.6 tok/s72.619:44gemma4:31bOllama4.5 tok/s75.918:40gemma4:26bOllama25.6 tok/s64.6