slotstream: Run a 105 GB AI model on a Mac that can't hold it

by carloslfu · Codex Skill · ★ 673

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Security audit verdict: SAFE · quality 66/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

apple-siliconclaude-codeinference-enginellmllm-inferencelocal-ailocal-llmmacosmetalmixture-of-experts

Quick Facts

Stars673
Forks54
LanguageSwift
CategoryCodex Skill
LicenseMIT
Quality Score66/100
Open Issues3
Last Updated2026-11-17
Created2026-08-28
Platformsclaude-code, cli, codex
Est. Tokens~19k

About slotstream

slotstream Run a 105 GB AI model on a Mac that can't hold it. Slotstream runs Qwen3.8-Flash-Next, a 125-billion-parameter open model, on Macs with 16 to 64 GB of memory. It keeps most of the model on the SSD and loads the parts it needs as it writes. Our 48 GB M5 Pro measured 15.86 tokens per second at a 22 GB memory target (how it was measured).

Compatible Skills

These tools work well together with slotstream for enhanced workflows:

  • ovo-local-llm — semantic(0.40)+complementary+shared_fw(ollama,openai)+rare_topics+similar_pop+shared_platform (75%)
  • MTPLX — semantic(0.48)+complementary+shared_fw(openai)+rare_topics+similar_pop+shared_platform (74%)
  • Agent — semantic(0.16)+complementary+shared_fw(ollama,openai)+same_lang+similar_pop+shared_platform (72%)
  • Council — semantic(0.16)+complementary+shared_fw(ollama,openai)+same_lang+similar_pop+shared_platform (72%)
  • Rapid-MLX — semantic(0.37)+complementary+shared_fw(ollama,openai)+similar_pop+shared_platform (69%)

slotstream alternative? Top 6 similar tools

Looking for a slotstream alternative? If you're comparing slotstream with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • MTPLX by youssofal · ⭐ 2.7k

    The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenC

  • local-code-community by drawthingsai · ⭐ 171

    Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Pyth

  • mlx-dspark by ARahim3 · ⭐ 736

    Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash

  • mlx-serve by ddalcu · ⭐ 2.5k

    Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swif

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • kaggle-tpu-lab by ARahim3 · ⭐ 775

    Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine)

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Swift Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools