Dev Radar
Support
LiveUpdated 2026-10-30 20:27 UTC

sushi

sushi — Sushi 🍣 1.4.1 drops today, DS4.1 +47% prefill reaching 1400+ tok/s, get yours👌

sushi is Sushi 🍣 1.4.1 drops today, DS4.1 +47% prefill reaching 1400+ tok/s, get yours👌. It is ranked #808 on the Dev Radar, in AI dev tools, first seen 35 days ago and shared in 5 posts (38.2k views).

Visit github.com

What sushi says about itself

Sushi engine runs very high quality quant model in Apple Silicon, using hybrid affine/exl3 with special expert tuning techniques. - beamivalice/sushi

GitHub - beamivalice/sushi: Sushi engine runs very high quality quant model in Apple Silicon, using hybrid affine/exl3 with special expert tuning techniques. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation sushi Public Notifications You must be signed in to change notification settings Fork 29 ( 29 )…

What people said about sushi on X

Quantized to Hell and Back !! DeepSeek 4.1F 1017-STQ-1.75bpw is released with Sushi 🍣 1.4.0, its quality is comparable to oQ2.5e & rendered this grim reaper animation. ✅ 1m context ✅ 96GB & 128GB Mac ✅ tok/s - 1,000 prefill, 75 code, 45 prose 🍣👌 https://github.com/beamivalice/sushi

— @Beamsters1, 3 days ago · 234 likes · see the post

Sushi 🍣 DeepSeek 4.1 Flash 1017 - STQ 1.75 bits is almost there! Here's one real output from it, created by this quant itself. The packed quality is amazing, the best model so far that can do real work in your 128GB Apple Silicon, and ✅ 1m context. ⭐️ https://github.com/beamivalice/sushi

— @Beamsters1, 4 days ago · 126 likes · see the post

Sushi 🍣1.2.4 is here and it landed big upgrades! 📈Qwen3.8 Flash 2.6bpw runs +10-15% faster 📈Memory tuning for small RAM, up to +200k context for 32GB/48GB/64GB/96GB machine! 📈32GB M1 Max can run Qwen3.8 Flash 2bpw at 250k context, kv 8bits! 👉https://github.com/beamivalice/sushi

— @Beamsters1, 15 days ago · 70 likes · see the post

Alternatives to sushi

sushi in numbers

FAQ

What is sushi?

Sushi 🍣 1.4.1 drops today, DS4.1 +47% prefill reaching 1400+ tok/s, get yours👌 It was first shared on X 35 days ago and is ranked #808 on the Dev Radar.

Is sushi free?

It is open source.

Who shared sushi?

1 account on X, including @Beamsters1, in 5 posts totalling 38.2k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.