Slotstream: run a 105GB Flash-Next on a 48GB Mac

Streams expert weights from SSD so a Mac that cannot hold the model in memory still runs it at roughly 12 tok/s. A neat trick for memory-poor Apple machines.

Open on GitHub

Preview of Slotstream: run a 105GB Flash-Next on a 48GB Mac

Launch: Qwen3.8-Flash-Next
Use case: Apple silicon
Format: Tool
Source: github.com

Carlos Galarza

shipping local AI and making it run efficiently

See all

Niko1221

@Niko1221 · Sep 24

Open-source inference engine with an OpenAI/Anthropic-style local API that fits the 125B MoE onto a 12GB consumer GPU plus system RAM. The project behind the model's local-running surge.

MiaAI-Lab

@MiaAI-Lab · Sep 4

Step-by-step recipe to squeeze the 125B model onto one DGX Spark instead of two, with config and measured throughput.

peonist-ai

@peonist-ai · Aug 26

Container-based server tuned for the gfx1151 Strix Halo APU, aimed at squeezing maximum tokens per second from the 125B model on a mini-PC.

slee-persis

@slee-persis · Aug 26

Ensemble harness claiming a group of small Qwen3.8 models reach frontier-level coding scores at a fraction of the cost. Results are self-reported and worth verifying.

Open on GitHub

Slotstream: run a 105GB Flash-Next on a 48GB Mac

More built with Qwen3.8-Flash-Next