Configs › DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated on Mac Ultra: 29.6 tok/s measured
DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated on Mac Ultra: 29.6 tok/s measured
Measured DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated speeds: 29.6 tok/s on Mac Ultra (MXFP4, mlx). 1 config, each linked to its source, snapshot 2026-10-16.
Snapshot 2026-10-16 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Quick answers
- How fast is DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated on Mac Ultra?
- 29.6 tok/s single-stream decode (MXFP4, mlx), the only measured config on Apple Mac Studio (M-series Ultra), measured by drowzeys, source last checked 2026-08-29. source
Measured configs for DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated | Mac Ultra | MXFP4 | mlx | 29.6 tok/s (prefill 454) | 1048576 | Extracted, source-linked | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.