Machine
Apple M4 Pro · Apple M4 Pro #49435834
5 runs of 2 models since Oct 21, 2026. Last run Nov 4, 2026.
5
runs
2
models
3
configs
1
configs run 2+ times
Hardware
- GPU
- Apple M4 Pro 48 GB
- CPU
- Apple M4 Pro 14 cores
- RAM
- 48 GB
- OS
- macOS 26.6.2
- Tools
- oMLX 3 · Rapid-MLX 1 · Strata 1
- Client
- 0.4.98
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
Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit
4 runs · 2 configs
★ bestoMLX256k ctxthinking default
×3 runs
76.072.7–79.8
steady
102 tok/s
101–103
qwen3.8-flash-next-q2_0
1 run · 1 config