DeepSeek V4.1 Flash 552B (16B active)
on M3 Ultra 256GB · Unsloth Studio
Summary
User reports DeepSeek V4.1 Flash at 40 t/s output on a Mac Studio with 256GB, run through Unsloth at IQ3_XXS.
The user finds it slow in practice, saying it takes 5-10 minutes to finish plotting a map that GLM 5.3 Flash finishes in a minute or so.
They ask whether others use speculative decoding and what effort level to set.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.
DeepSeek V4.1 Flash 552B · 16B active at 3-bit by hardware
- 73.4 t/s · one run
- 40.0 t/s · one run
Bars are medians on one scale, 0 to 73.4 tokens/s. Press ▶ to watch text arrive at a row's speed.
Models most run on the M3 Ultra 256GB
- 22.0 t/s · one run
- 40.0 t/s · one run
- 37.4 t/s · one run
- 25.0 t/s · one run
- Qwen3.5 9B4-bit107.5 t/s · one run
- 136.0 t/s · one run
Bars are medians on one scale, 0 to 136.0 tokens/s. Press ▶ to watch text arrive at a row's speed.
Everything reported on the M3 Ultra 256GB →Every DeepSeek V4.1 Flash report →Estimate DeepSeek V4.1 Flash on this card →