mlx-dspark benchmarks
An inference engine for running open-weight LLMs locally.
2 community reports
mlx-dspark results by GPU
Hardware with reported mlx-dspark results, with each report's model, quant and speed, newest first. Runs on several cards, with speculative decoding, with batched requests or with part of the model in system RAM say so, since each describes a different setup. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
mlx-dspark on M4 Pro 48GB1 report
- Muse 30B · 8-bit8.2 t/s
mlx-dspark on M5 Max 128GB1 report
- Qwen3.8 27B · 8-bit39.9 t/s(speculative)
This engine doesn't yet have an editorial profile on llamaperf. The community reports below show how it's been used in practice across different hardware.
Compare GPUs running mlx-dspark
Every card is compared on one model, Muse 30B at 8-bit, the size and bit class that most cards here have plain runs of. A card with no run of that model shows none rather than a figure from a different model.
| GPU | VRAM | Reports | Median speed, Muse 30B 8-bit |
|---|---|---|---|
| M4 Pro 48GBapple | 48GB | 1 | Gen 8.2 t/s |
| M5 Max 128GBapple | 128GB | 1 | no Muse 30B 8-bit run reported |
mlx-dspark against other engines
Pairs of plain runs on the same card, of the same model size at the same bit class: one device, one request, no speculative decoding, the whole model in memory. Context length and build still differ between the two sides, and each side shows its own.
No matched pair yet. No card has plain runs of one model size at one bit class on mlx-dspark and on another engine, so llamaperf can't say how it compares on speed. Add a run.
Top models on mlx-dspark
Frequently asked
Is mlx-dspark faster than other engines?
llamaperf has no matched comparison for mlx-dspark yet: no card has plain runs of the same model size at the same bit class on mlx-dspark and on another engine. Speed claims about engines need that pairing, so this page doesn't make one.