Which Mac runs which LLM, and how fast
Pick a Mac and a model, get the memory it needs and the tokens/sec to expect. Covers M1 to M6, every unified memory size, Q4 to FP16. Formula fitted and validated on our own measurements on two machines.
Which Mac runs which LLM, and how fast launched on October 17, 2026 with 10 votes, #549 of 3,080 launches that month and more than 90% of that year's launches.
In plain words
This tool helps users determine which large language models run on their Mac and at what speed. Users select their Mac model and desired LLM to discover memory requirements and token generation rates across M1 to M6 chips with various memory configurations and weight quantizations. The calculator uses formulas validated through direct measurements, providing estimates for both model fit and performance benchmarks based on unified memory capacity and bandwidth constraints.
written from the facts on this page · October 2026
From the sources
Two numbers decide everything about running a model locally on Apple Silicon. Whether it fits in unified memory, which is arithmetic on the parameter count. And how fast it generates, which is memory bandwidth divided by the size of the weights. Pick your Mac and your model below and the calculator does both. Expect roughly 5.7 tokens/sec of generation. The weights are 42.8 GB, the 8K tokens context adds about 1 GB, and 53.2 GB of your 64 GB is spoken for once macOS is accounted for. $ 197 /mo billed annually, or $ 286 /mo billed monthly. A dedicated machine with Ollama and an OpenAI compatible endpoint, ready in about 5 minutes. That answer costs money. 56 GB of unified memory is not a…from macyou.co
Does a similar job
all alternatives →
Llmspeed – feel how fast a local LLM runs before you buy the hardware4d ago · llmspeed.dev · ▲329Pick hardware and a model, and feel the real speed of a local LLM before you buy. Simulates tokens/sec and time-to-first-token from verified benchmarks for GPUs, Macs, and more.
Find the best local LLM for your hardware, ranked by benchmarksMay 2026 · github.com · ▲283Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
LLM StatsOct 2025 · llm-stats.com · ▲293I was overspending on GPT-4o. It was really hard to compare different models I could switch to, so I built this LLM comparison tool. It shows leaderboards, pricing, and performance data across 100+ LLMs (including all major providers and open-source models). Key features: - Live pricing comparisons - Benchmark Scores (MMLU, HumanEval, GPQA, etc.) - Context length vs cost analysis - Speed/throughput tests across providers - Quality vs price visualizations - Open source (all data verifiable) Try it out: https://llmstats.com I'd like to know your opinion :) Tech stack: Next.js,…
Ollama – Run LLMs on your Mac2023 · github.com · ▲284Hi HN A few folks and I have been working on this project for a couple weeks now. After previously working on the Docker project for a number of years (both on the container runtime and image registry side), the recent rise in open source language models made us think something similar needed to exist for large language models too. While not exactly the same as running linux containers, running LLMs shares quite a few of the same challenges. There are "base layers" (e.g. models like Llama 2), specific configuration to run correctly (parameters, temperature, context window sizes etc). There's…
KVSplit – Run 2-3x longer contexts on Apple Silicon2025 · github.com · ▲272I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…
LocalScore – Local LLM Benchmark2025 · localscore.ai · ▲124Hey Folks! I've been building an open source benchmark for measuring local LLM performance on your own hardware. The benchmarking tool is a CLI written on top of Llamafile to allow for portability across different hardware setups and operating systems. The website is a database of results from the benchmark, allowing you to explore the performance of different models and hardware configurations. Please give it a try! Any feedback and contribution is much appreciated. I'd love for this to serve as a helpful resource for the local AI community. For more check out: - Website:…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 19d ago · stillwet.art
Launched alongside, October 2026
the whole month →- IV
Life & fun · 13d 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 · 14d ago · bigwords.page
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 · 11h ago · permit.petercai.com
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 · 7d ago · guitoro.com