# ✅ BENCHMARKED: TensorFold made Qwen3.8 27B more than 3x faster on my 64GB M5 Pro Mac mini, on two versions in one day

**URL:** <http://gitLair.com/t/benchmarked-tensorfold-made-qwen3-8-27b-more-than-3x-faster-on-my-64gb-m5-pro-mac-mini-on-two-versions-in-one-day/186>\
**Category:** AI Hardware\
**Created:** [November 4, 2026, 3:01pm UTC](http://gitLair.com/t/benchmarked-tensorfold-made-qwen3-8-27b-more-than-3x-faster-on-my-64gb-m5-pro-mac-mini-on-two-versions-in-one-day/186 "2026-11-04T15:01:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![AOY](http://gitLair.com/user_avatar/gitLair.com/aoy/32/52_2.png) [@AOY](http://gitLair.com/u/AOY)\
**Post date:** [November 4, 2026, 3:01pm UTC](http://gitLair.com/t/benchmarked-tensorfold-made-qwen3-8-27b-more-than-3x-faster-on-my-64gb-m5-pro-mac-mini-on-two-versions-in-one-day/186/1 "2026-11-04T15:01:32Z")

</div>

✅ BENCHMARKED: TensorFold made Qwen3.8 27B more than 3x faster on my 64GB M5 Pro Mac mini, on two versions in one day.

In the morning I tested 1.2.1. On its own, the model wrote about 17 tokens a second. I then switched on the DFlash2 drafter, a small helper that guesses the next few tokens so the big model only has to check them and it jumped to 56.

And later in the afternoon  
@ashxhart  
shipped 1.2.2. His release notes focused on other hardware, so I reran everything on my Mac mini.

On mine it runs within a few percent of 1.2.1, and the drafter still makes it 3x faster. With randomness off, the answer came out word for word the same as without the drafter.

- Chat, 3.26x faster on 1.2.1 and 3.35x on 1.2.2
- A 31K token prompt, 2.94x and 2.77x
- Code, 5.4x and 5.5x, up to 91.90 tokens a second
- 28.5 GiB peak memory on both
- New in 1.2.2, the first request doesn’t wait for the drafter to load

A massive thanks to  
@ashxhart  
and all the contributors behind 1.2.2.

The TensorFold challenge from  
@YukonResearch  
is open until Nov 6th if you want to try pushing it further on your own Mac.