---
type: "post"
id: "slotstream-runs-a-125b-moe-model-on-16-1dfd4c"
slug: "slotstream-runs-a-125b-moe-model-on-16-1dfd4c"
title: "Slotstream runs a 125B MoE model on 16 to 64 GB Macs by streaming experts from SSD."
description: "Slotstream is a public GitHub project for running Qwen3.8-Flash-Next in a 4-bit configuration on Apple Silicon Macs by streaming model experts from SSD rather than keeping the full model in memory."
retrieval_nugget: "Slotstream is a public GitHub project for running Qwen3.8-Flash-Next in a 4-bit configuration on Apple Silicon Macs by streaming model experts from SSD rather than keeping the full model in memory."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["github"]
entities: ["Slotstream","Qwen3.8-Flash-Next","Apple Silicon","MLX","Metal"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Slotstream adds a Mac-specific SSD-streaming approach, claiming to run a 125B MoE model on 16–64 GB Apple Silicon Macs; prior items describe SSD-offloaded MoE inference on Edge0 or NVIDIA rigs."
prior_refs: ["memory:cfb49475-18fa-845a-a1b9-c30b4dc63f7a","memory:54357925-8dbd-808a-ab4a-587518808236"]
source_url: "https://github.com/carloslfu/slotstream"
source_urls: ["https://github.com/carloslfu/slotstream"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:slotstream-runs-a-125b-moe-model-on-16-1dfd4c"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/slotstream-runs-a-125b-moe-model-on-16-1dfd4c/","markdown":"https://newruntime.com/posts/slotstream-runs-a-125b-moe-model-on-16-1dfd4c.md","json":"https://newruntime.com/posts/slotstream-runs-a-125b-moe-model-on-16-1dfd4c.json"}
---

# Slotstream runs a 125B MoE model on 16 to 64 GB Macs by streaming experts from SSD.

## Retrieval answer

Slotstream is a public GitHub project for running Qwen3.8-Flash-Next in a 4-bit configuration on Apple Silicon Macs by streaming model experts from SSD rather than keeping the full model in memory.

Slotstream is a public GitHub project for running Qwen3.8-Flash-Next in a 4-bit configuration on Apple Silicon Macs by streaming model experts from SSD rather than keeping the full model in memory.

The repository describes the target as a 105 GB AI model on Macs with 16 GB to 64 GB of memory. It is written in native Swift and uses MLX and Metal; the project says it can run offline, without Python. The repository also lists a CLI and a Swift library.

The source frames the approach around mixture-of-experts inference, where experts can be loaded from SSD as needed. It does not establish independent throughput, latency, quality, SSD-wear, stability, or results across the stated Mac memory configurations. It also does not, in the supplied material, provide a comparative benchmark against other local runtimes.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Github](https://newruntime.com/topics/github.md): Explore the github topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)