Life & fun · September 1, 2026
Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!
Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s launched on September 1, 2026 with 240 votes, #71 of 8,094 launches that month and more than 99% of that year's launches.
In plain words
SlotStream enables users to run the Qwen3.8-Flash-Next 125B mixture-of-experts model on Mac computers with limited RAM by streaming model components from storage to memory as needed. Built with MLX and Swift, it uses 4-bit quantization to reduce the 104GB model to manageable sizes and provides an Ollama-compatible API for integration with existing tools. It targets developers who need access to large language models on Mac hardware without sufficient VRAM.
written from the facts on this page · September 2026
From the sources
Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients. - carloslfu/slotstream
Does a similar job
all alternatives →
Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput2025 · github.com · ▲123Contribute to Mega4alik/ollm development by creating an account on GitHub.
Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhoneAug 2026 · github.com · ▲312Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone. - leonickson1/Swiftlet
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
80% faster, 50% less memory, 0% loss of accuracy Llama finetuning2023 · github.com · ▲385Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
Qwen3.8-MaxAug 2026 · qwen.ai · ▲277Qwen3.8-Max + MCP for coding on your local machine, without paying for Qwen Code. Qwen3.8-Max itself runs in the cloud through Qwen Studio — this setup just gives it access to your local files and terminal through MCP. My take: it is slower than Codex and Claude Code, especially in thinking mode, but it does work well. MCP adds some latency too since there’s an extra layer between the model and your machine. In fast mode, it gets noticeably closer. I wouldn’t put it in the same category as Fable or Opus-5. Personally, I’d place it closer to the next Opus 4.7 level in terms of coding ability.…
More life & fun this month
the category →
A free city-building game in your browser. You are the mayor. You know what the city needs. Now get it past the zoning board, the neighbors, the appeals court and the next election.
Life & fun · 3d ago · permit.petercai.com
- IV
Life & fun · 16d ago · tanzaniaeducationproject.org
Turn a phone, tablet or TV into a sign. Type a message and it fills the screen: welcome signs, timers, Wi-Fi passwords and more. No app, no account, free.
Life & fun · 16d ago · bigwords.page
Play a free virtual guitar online with your keyboard or by touch. Slow songs down and see every chord, string and strum. Acoustic, classic, electric and bass.
Life & fun · 10d ago · guitoro.com
Carrier settings from iPhone, Pixel and Galaxy firmware, decoded and compared: APNs, VoLTE, 5G and Wi-Fi Calling per carrier, and what each build changed.
Life & fun · 14d ago · carrierexplode.com
Life & fun · 24d ago · space.bl2.net
Launched alongside, September 2026
the whole month →
E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
AI · Sep 2026 · github.com
- WI
Special relativity simulator in which light crawls along at a human speed, so Lorentz contraction, aberration and Doppler shift happen at walking pace.
Life & fun · Sep 2026 · rivendell.dmitrybrant.com
Start coding agents, control sessions, review PRs. Anywhere.
Dev tools · Sep 2026 · kilo.ai
