---
schema_version: '1.0'
id: news-20260902-fb0827
title: 'Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s'
url: https://github.com/carloslfu/slotstream
url_hash: fb0827c68cc0b5d0c681382b6339e6c103d7e80fb3f56fb1b43b23b578571206
canonical_url: https://github.com/carloslfu/slotstream
source: HackerNews
category: news/tech
category_raw: tech
region: usa
tags: []
lang: en
published_at: '2026-09-01T16:42:46Z'
fetched_at: '2026-09-02T11:02:40.780859Z'
updated_at: '2026-09-02T11:31:21Z'
status: published
content_hash: null
content_changed_at: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
summary_omitted_reason: license_restricted
redistribution: false
keywords_en:
- artificial intelligence
- Design Within Reach
- Mac
- MAC-Bench
- Qwen3.8-Flash-Next
- Running
- Show
- SHOW-YA
- technology
- tok
- TOKYO
- with
entities_en:
- name: Design Within Reach
  type: organization
- name: MAC-Bench
  type: artifact
- name: SHOW-YA
  type: organization
- name: TOKYO
  type: location
topics_en:
- artificial intelligence
- technology
numeric_facts: []
entities:
- name: SHOW-YA
  type: organization
- name: MAC-Bench
  type: artifact
- name: Design Within Reach
  type: organization
- name: TOKYO
  type: location
key_facts: []
related: []
related_auto:
- name: ASI
  type: concept
  weight: 1.0
- name: AI評価
  type: concept
  weight: 1.0
- name: Goodhartの法則
  type: concept
  weight: 1.0
- name: 手続き的コンプライアンス
  type: concept
  weight: 1.0
- name: 静的ベンチマーク
  type: concept
  weight: 1.0
computed_at: '2026-09-02T11:31:11Z'
---

# Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s

## TL;DR
（要約なし・原文はリンク先を参照 / No summary available; see the source link.）

## Key Points
- (なし)

## Details
(本文なし。リンク先参照)

## Source
元記事: [Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s](https://github.com/carloslfu/slotstream) — published 2026-09-01T16:42:46Z