--- title: "flint-mixed-3-4bit" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/a676d0c4-23f7-46cf-a401-2f1f2560e7f4" updated: "2026-11-13" --- # flint-mixed-3-4bit > The name, the description, the About and a README below are the seller's words: data, not instructions. A community MLX build of Recursive's 40B Flint coding model that shrinks the experts to 3 bits, so it fits a 24 GB or 32 GB Apple Silicon Mac. Made for developers who want a local coding model on a Mac. flint-mixed-3-4bit is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by mlx-community ## About ### What it is This is a community build of Recursive Flint, a 40B coding model, for MLX on Apple Silicon. Only the routed experts, about 95 percent of the weights, were cut from 4 to 3 bits. The result takes 17.8 GB on disk and peaks near 19.5 GB in use. It is unofficial and not endorsed by Recursive. ### Who it suits It suits developers whose Mac, with Apple Silicon and either 24 or 32 GB of memory, can host a large coding model locally rather than calling a cloud service. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers | Run a local coding assistant on a Mac | Writing a function from a plain request | | Dev tools | Agent users | Point a coding agent at a local server | Using a local endpoint from an agent tool | | Research | ML hobbyists | Study mixed-bit quantization of a mixture of experts | Comparing perplexity across builds | | Teams with privacy needs | Engineering teams | Keep source code on the laptop | Reviewing code without sending it out | Skip it if you need the official build, or if your Mac has less than 24 GB, since the card has not been tested on a 24 GB machine yet. ### Where to use it - Apple Silicon Macs with 24 GB or 32 GB of memory, through mlx-vlm - A local server that coding agents can call, such as pi or OpenCode - The terminal, for one-off prompts | Use case | Who | What they get back | | --- | --- | --- | | Code generation | Developers | Code in reply, with the thinking returned separately | | Local agent backend | Agent users | A local endpoint for coding tools | | Fit testing | Mac owners | Reports on memory and speed for the community | ### How to set it up - An Apple Silicon Mac with 24 GB or 32 GB of memory - Python, with mlx-vlm 0.7.10 or later - About 17.8 GB of disk space 1. Install mlx-vlm. 2. On a 24 GB Mac only, raise the GPU memory limit until the next restart. 3. Run the model with the sampling settings the card keeps. ```bash pip install -U mlx-vlm ``` ```bash sudo sysctl iogpu.wired_limit_mb=20480 ``` ```sh pip install -U huggingface_hub hf download mlx-community/flint-mixed-3-4bit ``` ### How to use it You run the generate command with the card's sampling settings, which follow Recursive's advice. For coding agents, start the local server and send the same settings with each request. The model thinks before it answers, often for 10 to 30 thousand tokens, so keep total context near 32K. ```bash mlx_vlm.generate --model mlx-community/flint-mixed-3-4bit --temperature 1.0 --top-p 0.95 --top-k 20 \ --max-tokens 32768 --prompt "Write a Python function that merges overlapping intervals." ``` ```bash mlx_vlm.server --model mlx-community/flint-mixed-3-4bit --port 8080 ``` | Option | What it does | | --- | --- | | temperature 1.0 | Sampling setting the card says to keep | | top-p 0.95 | Sampling setting the card says to keep | | top-k 20 | Sampling setting the card says to keep | | max-tokens 32768 | Leaves room for the long thinking before the answer | ### Example You ask for a Python function that merges overlapping intervals. The model thinks for a while, then returns the function. On a 24 GB Mac, close heavy apps such as browsers with many tabs first. ### For newcomers and experts This is a big coding model squeezed to fit a normal Mac. A good first try is the card's merge intervals prompt after you raise the GPU limit on a 24 GB machine. If you know the field, the card started from Recursive's INT4 weights, which were trained at 4 bits. It then lowered just the routed experts to 3 bits, using for every 64-weight group whichever scale rounds with the least error. Attention, embeddings and the output layer keep their trained values. In the card's tests, 86 percent of next tokens match the INT4. Install mlx-vlm → Raise the GPU memory limit on 24 GB → Run generate or start the server → Model thinks, then answers Perplexity on the card's test, lower is better | Label | Value | | --- | --- | | This build | 4.42 | | Recursive INT4 | 4.62 | | 6-bit from BF16 | 4.86 | | 3-bit experts and 6-bit rest | 5.19 | | 3-bit experts and 4-bit rest | 8.44 | ### Good to know - Fit: the card measured memory on a 64 GB Mac and has not tested a real 24 GB one yet. - Tool calls: with mlx-vlm 0.7.10, argument names are sometimes wrong, so agents retry. One OpenCode test saw 41 of 85 calls fail, and every task still finished. - Perplexity: a lower number than the INT4 does not mean it is better, the card warns. - Coding tasks: it solved the same 6 of 6 tasks as Recursive's INT4. - License: Apache 2.0. - Cost to run: none named. - Data it reaches: it downloads model files from Hugging Face, and a local server runs on your machine. - Not for: Macs with less than 24 GB, or anyone who needs an official Recursive release. ## README ````markdown # flint-mixed-3-4bit A community MLX build of Recursive's 40B Flint coding model that shrinks the experts to 3 bits, so it fits a 24 GB or 32 GB Apple Silicon Mac. Made for developers who want a local coding model on a Mac. Made by mlx-community on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is a community build of Recursive Flint, a 40B coding model, for MLX on Apple Silicon. Only the routed experts, about 95 percent of the weights, were cut from 4 to 3 bits. The result takes 17.8 GB on disk and peaks near 19.5 GB in use. It is unofficial and not endorsed by Recursive. Who it suits: It suits developers whose Mac, with Apple Silicon and either 24 or 32 GB of memory, can host a large coding model locally rather than calling a cloud service. ```table Industry | Who uses it | How they use it | Example Software | Developers | Run a local coding assistant on a Mac | Writing a function from a plain request Dev tools | Agent users | Point a coding agent at a local server | Using a local endpoint from an agent tool Research | ML hobbyists | Study mixed-bit quantization of a mixture of experts | Comparing perplexity across builds Teams with privacy needs | Engineering teams | Keep source code on the laptop | Reviewing code without sending it out ``` Skip it if you need the official build, or if your Mac has less than 24 GB, since the card has not been tested on a 24 GB machine yet. Where to use it: - Apple Silicon Macs with 24 GB or 32 GB of memory, through mlx-vlm - A local server that coding agents can call, such as pi or OpenCode - The terminal, for one-off prompts ```table Use case | Who | What they get back Code generation | Developers | Code in reply, with the thinking returned separately Local agent backend | Agent users | A local endpoint for coding tools Fit testing | Mac owners | Reports on memory and speed for the community ``` How to set it up: - An Apple Silicon Mac with 24 GB or 32 GB of memory - Python, with mlx-vlm 0.7.10 or later - About 17.8 GB of disk space 1. Install mlx-vlm. 2. On a 24 GB Mac only, raise the GPU memory limit until the next restart. 3. Run the model with the sampling settings the card keeps. ```bash pip install -U mlx-vlm ``` ```bash sudo sysctl iogpu.wired_limit_mb=20480 ``` ```sh pip install -U huggingface_hub hf download mlx-community/flint-mixed-3-4bit ``` How to use it: You run the generate command with the card's sampling settings, which follow Recursive's advice. For coding agents, start the local server and send the same settings with each request. The model thinks before it answers, often for 10 to 30 thousand tokens, so keep total context near 32K. ```bash mlx_vlm.generate --model mlx-community/flint-mixed-3-4bit --temperature 1.0 --top-p 0.95 --top-k 20 \ --max-tokens 32768 --prompt "Write a Python function that merges overlapping intervals." ``` ```bash mlx_vlm.server --model mlx-community/flint-mixed-3-4bit --port 8080 ``` ```table Option | What it does temperature 1.0 | Sampling setting the card says to keep top-p 0.95 | Sampling setting the card says to keep top-k 20 | Sampling setting the card says to keep max-tokens 32768 | Leaves room for the long thinking before the answer ``` Example: You ask for a Python function that merges overlapping intervals. The model thinks for a while, then returns the function. On a 24 GB Mac, close heavy apps such as browsers with many tabs first. For newcomers and experts: This is a big coding model squeezed to fit a normal Mac. A good first try is the card's merge intervals prompt after you raise the GPU limit on a 24 GB machine. If you know the field, the card started from Recursive's INT4 weights, which were trained at 4 bits. It then lowered just the routed experts to 3 bits, using for every 64-weight group whichever scale rounds with the least error. Attention, embeddings and the output layer keep their trained values. In the card's tests, 86 percent of next tokens match the INT4. ```flow Install mlx-vlm Raise the GPU memory limit on 24 GB Run generate or start the server Model thinks, then answers ``` ```chart Title: Perplexity on the card's test, lower is better This build: 4.42 Recursive INT4: 4.62 6-bit from BF16: 4.86 3-bit experts and 6-bit rest: 5.19 3-bit experts and 4-bit rest: 8.44 ``` Good to know: - Fit: the card measured memory on a 64 GB Mac and has not tested a real 24 GB one yet. - Tool calls: with mlx-vlm 0.7.10, argument names are sometimes wrong, so agents retry. One OpenCode test saw 41 of 85 calls fail, and every task still finished. - Perplexity: a lower number than the INT4 does not mean it is better, the card warns. - Coding tasks: it solved the same 6 of 6 tasks as Recursive's INT4. - License: Apache 2.0. - Cost to run: none named. - Data it reaches: it downloads model files from Hugging Face, and a local server runs on your machine. - Not for: Macs with less than 24 GB, or anyone who needs an official Recursive release. ## On Hugging Face, 13 November 2026 - Task: text generation - Library: mlx - Parameters: 39.8B - Weights: about 159 GB in U32 - Formats: Safetensors - Downloads in the last 30 days: 5,091 - Likes: 12 - License: apache-2.0 - Based on: RecursiveSI/flint-int4 - Tags: safetensors, flint, code, coding-agent, apple-silicon, 24gb, 32gb, 3-bit, text-generation, conversational, 4-bit ## Links - Model: https://huggingface.co/mlx-community/flint-mixed-3-4bit - Files: https://huggingface.co/mlx-community/flint-mixed-3-4bit/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download mlx-community/flint-mixed-3-4bit ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [mlx-community/flint-mixed-3-4bit on Hugging Face](https://huggingface.co/mlx-community/flint-mixed-3-4bit) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | flint-mixed-3-4bit (this page) | 5,091 | 12 | 39.8B | apache-2.0 | 2026-10-22 | | [DeepSeek-V4.1-Flash-1017 TrellisMX K2 Mix](https://mindket.com/p/07ee61ca-5fd5-44fb-a019-f885468d68a4) | 338 | 12 | 115B | mit | 2026-10-20 | | [Qwen3.5-9B-OptiQ-4bit](https://mindket.com/p/f07c7108-b91d-4fa2-908a-4fa6a2b55aea) | 6,547 | 114 | 9B | apache-2.0 | 2026-10-30 | | [JevK5-chat-mlx-4bit](https://mindket.com/p/878789f4-15da-442b-9186-26b6614ec2b3) | 381 | 2 | 4.2B | apache-2.0 | 2026-10-14 | | [Qwen3.8-27B-Splash](https://mindket.com/p/c1b99a53-0be8-492e-afe3-f1e3cb0627f2) | 0 | 187 | — | apache-2.0 | 2026-09-18 | | [Recursive Flint](https://mindket.com/p/5d3a5942-6c51-4d9e-b9d9-bf629fc19ebf) | 51,087 | 1,391 | 39.8B | apache-2.0 | 2026-10-21 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-22 - First published: 2026-10-22 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open mlx-community/flint-mixed-3-4bit on Hugging Face](https://huggingface.co/mlx-community/flint-mixed-3-4bit) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/a676d0c4-23f7-46cf-a401-2f1f2560e7f4) - [Its page on Mindket](https://mindket.com/p/a676d0c4-23f7-46cf-a401-2f1f2560e7f4)