The fastest way to run Mixtral 8x7B on Apple Silicon Macs
I’d originally launched my app: Private LLM[1][2] on HN around 10 months ago, with a single RedPajama Chat 3B model. The app has come a long way since then. About a month ago, I added support for 4-bit OmniQuant quantized Mixtral 8x7B Instruct model, and it seems to outperform Q4 models at inference speed and Q8 models at text generation quality, while consuming only about 24GB of RAM[3] at 8k context length. The trick is: a) to use a better quantization algorithm and b) to use unquantized embeddings and the MoE gates (the overhead is quite small). Other notable features include many more…
The fastest way to run Mixtral 8x7B on Apple Silicon Macs launched on April 8, 2024 with 18 votes, #888 of 4,347 launches that month and more than 75% of that year's launches.
In plain words
Private LLM is a macOS and iOS application that runs large language models locally on Apple Silicon devices. It supports multiple models including a 4-bit quantized Mixtral 8x7B that operates efficiently on 24GB of RAM while maintaining fast inference speed and high text quality. The app offers features like grammar correction, summarization, Siri integration, and Apple Shortcuts support, making it suitable for users seeking private, on-device AI capabilities without cloud dependencies.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I’d originally launched my app: Private LLM[1][2] on HN around 10 months ago, with a single RedPajama Chat 3B model. The app has come a long way since then. About a month ago, I added support for 4-bit OmniQuant quantized Mixtral 8x7B Instruct model, and it seems to outperform Q4 models at inference speed and Q8…
Does a similar job
all alternatives →
Speeding up LLM inference 2x times (possibly)2024 · asciinema.org · ▲419Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
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…
- WMWe made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲161
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
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…
- IBI built an on-device LLM based chatbot for iPhones2023 · ▲20
I’ve been playing around with local LLMs for the past couple of months and decided to build something that can run on an iPhone. It’s a universal app built with SwiftUI and the excellent ggml library. The model is an SFT fine tuned and 4 bit quantised version of the RedPajama-INCITE-Chat-3B-v1 OSS LLM. It works reasonably well on recent-ish (~3 year old) iPhones, iPads and Macs. It was launched on the App Store yesterday[1] and Product Hunt today[2]. It seems to be reasonably ok at natural language interactions, but given its size, does pretty badly at coding and reasoning. Also, it…
Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/sSep 2026 · github.com · ▲240I 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!
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 24d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, April 2024
the whole month →
Supabase▲2,325The Postgres developer platform is now generally available
Dev tools · 2024 · supabase.com
Cal.com Platform▲1,601Build your pixel-perfect booking experience with Atoms
Dev tools · 2024 · cal.com
deco.cx 2.0▲1,078Build web apps 10x faster with Deno, JSX, TS & Tailwind
Dev tools · 2024 · decocms.com
