cd /news/large-language-models/deepseek-v4-1-flash-runs-23-seconds-… · home topics large-language-models article
[ARTICLE · art-127392] src=twitter.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

DeepSeek v4.1 flash runs 23 seconds/token on a 2020 16gb M1 Mac Mini

A developer posting as FP4 Brain on X reported running DeepSeek V4.1 Flash locally on a 16GB M1 Mac Mini using original FP4/FP8 weights, SSD streaming, and a custom MLX runner built on the pipenetwork MLX port, achieving 108 seconds time-to-first-token and about 23 seconds per token. The developer said the setup improved from roughly 31 to 23 seconds per token by reusing allocation buffers, compiling weight decoding, and caching 4 GiB of dense weights, keeping weights on the SSD with selected experts and lookup rows loaded on demand; a 6 GiB cache was tried but was barely faster with more swapping. Code, tests, and logs are published in the GitHub repository atbender/deeps.

read1 min views3 publishedSep 12, 2026
DeepSeek v4.1 flash runs 23 seconds/token on a 2020 16gb M1 Mac Mini
Image: source

FP4 Brain on X: "got deepseek V4.1 flash running locally on a 16GB m1 mac mini original FP4/FP8 weights, ssd streaming + custom mlx runner 108s ttft and about 23s/token (not to be confused with tok/s)"

got deepseek V4.1 flash running locally on a 16GB m1 mac mini original FP4/FP8 weights, ssd streaming + custom mlx runner 108s ttft and about 23s/token (not to be confused with tok/s)

got deepseek V4.1 flash running locally on a 16GB m1 mac mini original FP4/FP8 weights, ssd streaming + custom mlx runner 108s ttft and about 23s/token (not to be confused with tok/s)

code + recipe if you're not in a hurry github.com/atbender/deeps… weights stay on SSD. the runner loads selected experts + lookup rows on demand, with a 4 GiB cache for dense weights. built on @pipenetwork MLX port

got it from about 31 to 23 seconds/token by reusing allocation buffers, compiling weight decoding and caching 4 GiB of dense weights tried 6 GiB too but it was meh, barely faster and more swapping. that's why I stuck with 4 if anyone's wondering tests + logs in the repo

── more in #large-language-models 4 stories · sorted by recency
backchannel.rpediter.com · · #large-language-models
Backchannel
── more on @deepseek v4.1 flash 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/deepseek-v4-1-flash-…] indexed:0 read:1min 2026-09-12 ·