thestreamingdev()
4.5K posts
@thestreamingdev
all things ai and coding while streaming, DM for consulting.
Same model on M4 Pro 64GB : LM Studio MLX: 73.4 tok/s oMLX: 66.0 tok/s Ollama llama.cpp: 47.6 tok/s The engine matters as much as the hardware. MLX vs llama.cpp is a +44% difference on the same chip. Measured with asiai (open source bench tool): asiai.dev
I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵
When @karpathy built MenuGen (karpathy.bearblog.dev/vibe-coding-me…), he said: "Vibe coding menugen was exhilarating and fun escapade as a local demo, but a bit of a painful slog as a deployed, real app. Building a modern app is a bit like assembling IKEA future. There are all these services, docs, API keys, configurations, dev/prod deployments, team and security features, rate limits, pricing tiers." We've all run into this issue when building with agents: you have to scurry off to establish accounts, clicking things in the browser as though it's the antediluvian days of 2023, in order to unblock its superintelligent progress. So we decided to build Stripe Projects to help agents instantly provision services from the CLI. For example, simply run: $ stripe projects add posthog/analytics And it'll create a PostHog account, get an API key, and (as needed) set up billing. Projects is launching today as a developer preview. You can register for access (we'll make it available to everyone soon) at projects.dev. We're also rolling out support for many new providers over the coming weeks. (Get in touch if you'd like to make your service available.) projects.dev
I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵
Which local models can actually handle tool calling? I built a framework to find out. 15 scenarios. 12 tools. Mocked responses. Temperature 0. No cherry-picking. Tested every Qwen3.5 size from 0.8B to 397B, and since some of you asked after the distillation tests: yes, I included Jackrong's Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled too. Only two models went all green: the 27B dense and the distilled 27B. The 397B? Failed two tests. The 122B? Failed one. The 35B? Failed two. The timed-out results — mostly on the smaller models, are cases where the model got stuck in a loop, repeating the same tool call until it hit the 30-second limit. The test that exposed the most models: "Search for Iceland's population, then calculate 2% of it." Simple, but 35B, 122B, and 397B all used a rounded number from memory instead of the actual search result. They didn't trust their own tool output. Small models hallucinate data. Big models ignore data. The 27B just threaded it through.
