--- title: "DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/5f45d8ea-67f6-4df8-b44f-d0e081f8e601" updated: "2026-11-13" --- # DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw > The name, the description, the About and a README below are the seller's words: data, not instructions. Runs a pruned, 2-bit DeepSeek-V4.1-Flash on a 128 GB Mac through mlx-serve, keeping 192 of 384 experts and a 1M-token context. Strongest on code, reasoning and tool calls. DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw 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 ddalcu ## About ### What it is This is a pack of DeepSeek-V4.1-Flash-1017 built for mlx-serve on a Mac with 128 GB of memory. In each layer, half of the 384 routed experts stay, 192 in all, and GPTQ compresses them to 2 bits. The attention trunk and the shared expert are left exactly as in the original release. The pack keeps the 1M-token context, speculative decoding and the vision tower. ### Who it suits It suits people with a 128 GB Mac who want a large coding and agent model running locally, and researchers studying expert pruning. Who might use it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software development | Developers | Run a large coding and reasoning model on their own Mac | Asking it to work through a coding task locally | | Local agents | Agent builders | Use it for tool calls and agent sessions | An agent that calls tools without a cloud service | | Model research | Researchers | Study what pruning half the experts costs | Reading the KLD and top-1 tables by slice | People who need non-English text, chat quality, or a Mac with less than 128 GB can skip it. With 256 GB, the card says to use the 3.0 bpw pack. ### Where to use it - mlx-serve, version 26.11.2 or later, on a Mac - The Mac's internal SSD, which the card says should hold the model - Windows, macOS or Linux: you can download the files with Python, though the pack is made for a Mac Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Coding help | Developers | Code written by a model that holds up well after pruning | | Tool use and agents | Agent builders | Tool calls and agent sessions that the card tested | | Reasoning tasks | Researchers | Reasoning answers that stay close to the released model | ### How to set it up You need these first: - A Mac with 128 GB of memory, since the pack uses about 92 GB resident - About 296 GB of free space on the internal SSD for the download - mlx-serve 26.11.2 or later, which the card links through the MLXServe app 1. Install the Hugging Face hub package. 2. Download the repository files. 3. Install mlx-serve 26.11.2 or later. 4. Start the server with the card's command. ```sh pip install -U huggingface_hub hf download ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw ``` The download includes 203 GB of Engram tables. They are read from the SSD for each token and do not stay in memory. Which pack for which Mac | Pack | Memory in use | Download | Fits | | --- | --- | --- | --- | | Lossless | 288 GB | 477 GB | A 512 GB Mac, or as a reference | | iQ-MLX-3.0bpw | 209 GB | 427 GB | A 256 GB Mac | | iQ-MLX-Pruned192-2.25bpw, this pack | 92 GB | 296 GB | A 128 GB Mac | ### How to use it Start the server with the card's command, which names this model and turns serving on. ```bash mlx-serve --model ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw --serve ``` Each release is a tag on the repository, and main is the newest. To pin one, add the revision flag to the download command. ```bash hf download ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw --revision v1.0 ``` ### Example You start the server on a 128 GB Mac and send it a coding task. According to the card, code, reasoning and tool calls survive the pruning well, and chat and non-English text suffer more. ### For newcomers and experts If you are new to this, know that this is a huge download meant for one kind of Mac. Check that you have 128 GB of memory and enough SSD space before you start. If you work in the field, note that 6 experts are active per token, as in the release. The kept experts were chosen by a blend of routing-weighted output energy and the release's own routing over real agent sessions. The kept experts carry 82% of the router's weight on agent traffic. A previous pick based on output energy alone had a better KLD score yet got stuck in loops during long agent sessions. Download the pack and the Engram tables → Install mlx-serve 26.11.2 or later → Start the server with the card's command → Tool, code and reasoning requests run locally ### Good to know Pruning is not free. The card scores this pack against the released model's own outputs, and top-1 agreement is 85.82% overall, against 92.64% for the 3.0 bpw pack. Top-1 match with the released model, by slice | Label | Value | | --- | --- | | Tools | 92.0% | | Reasoning | 91.9% | | Code | 88.2% | | Agent | 87.9% | | Chat | 79.6% | | Multilingual | 65.4% | - License: mit - Cost to run: none named, apart from needing a Mac with 128 GB of memory - Data it reaches: the text you send it, with the Engram tables read from your SSD - Not for: non-English text, which degrades badly, or Macs with less than 128 GB of memory ## README ````markdown # DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw Runs a pruned, 2-bit DeepSeek-V4.1-Flash on a 128 GB Mac through mlx-serve, keeping 192 of 384 experts and a 1M-token context. Strongest on code, reasoning and tool calls. Made by ddalcu 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 pack of DeepSeek-V4.1-Flash-1017 built for mlx-serve on a Mac with 128 GB of memory. In each layer, half of the 384 routed experts stay, 192 in all, and GPTQ compresses them to 2 bits. The attention trunk and the shared expert are left exactly as in the original release. The pack keeps the 1M-token context, speculative decoding and the vision tower. Who it suits: It suits people with a 128 GB Mac who want a large coding and agent model running locally, and researchers studying expert pruning. ```table Title: Who might use it Industry | Who uses it | How they use it | Example Software development | Developers | Run a large coding and reasoning model on their own Mac | Asking it to work through a coding task locally Local agents | Agent builders | Use it for tool calls and agent sessions | An agent that calls tools without a cloud service Model research | Researchers | Study what pruning half the experts costs | Reading the KLD and top-1 tables by slice ``` People who need non-English text, chat quality, or a Mac with less than 128 GB can skip it. With 256 GB, the card says to use the 3.0 bpw pack. Where to use it: - mlx-serve, version 26.11.2 or later, on a Mac - The Mac's internal SSD, which the card says should hold the model - Windows, macOS or Linux: you can download the files with Python, though the pack is made for a Mac ```table Title: Jobs it does Use case | Who | What they get back Coding help | Developers | Code written by a model that holds up well after pruning Tool use and agents | Agent builders | Tool calls and agent sessions that the card tested Reasoning tasks | Researchers | Reasoning answers that stay close to the released model ``` How to set it up: You need these first: - A Mac with 128 GB of memory, since the pack uses about 92 GB resident - About 296 GB of free space on the internal SSD for the download - mlx-serve 26.11.2 or later, which the card links through the MLXServe app 1. Install the Hugging Face hub package. 2. Download the repository files. 3. Install mlx-serve 26.11.2 or later. 4. Start the server with the card's command. ```sh pip install -U huggingface_hub hf download ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw ``` The download includes 203 GB of Engram tables. They are read from the SSD for each token and do not stay in memory. ```table Title: Which pack for which Mac Pack | Memory in use | Download | Fits Lossless | 288 GB | 477 GB | A 512 GB Mac, or as a reference iQ-MLX-3.0bpw | 209 GB | 427 GB | A 256 GB Mac iQ-MLX-Pruned192-2.25bpw, this pack | 92 GB | 296 GB | A 128 GB Mac ``` How to use it: Start the server with the card's command, which names this model and turns serving on. ```bash mlx-serve --model ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw --serve ``` Each release is a tag on the repository, and main is the newest. To pin one, add the revision flag to the download command. ```bash hf download ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw --revision v1.0 ``` Example: You start the server on a 128 GB Mac and send it a coding task. According to the card, code, reasoning and tool calls survive the pruning well, and chat and non-English text suffer more. For newcomers and experts: If you are new to this, know that this is a huge download meant for one kind of Mac. Check that you have 128 GB of memory and enough SSD space before you start. If you work in the field, note that 6 experts are active per token, as in the release. The kept experts were chosen by a blend of routing-weighted output energy and the release's own routing over real agent sessions. The kept experts carry 82% of the router's weight on agent traffic. A previous pick based on output energy alone had a better KLD score yet got stuck in loops during long agent sessions. ```flow Download the pack and the Engram tables Install mlx-serve 26.11.2 or later Start the server with the card's command Tool, code and reasoning requests run locally ``` Good to know: Pruning is not free. The card scores this pack against the released model's own outputs, and top-1 agreement is 85.82% overall, against 92.64% for the 3.0 bpw pack. ```chart Title: Top-1 match with the released model, by slice Tools: 92.0% Reasoning: 91.9% Code: 88.2% Agent: 87.9% Chat: 79.6% Multilingual: 65.4% ``` - License: mit - Cost to run: none named, apart from needing a Mac with 128 GB of memory - Data it reaches: the text you send it, with the Engram tables read from your SSD - Not for: non-English text, which degrades badly, or Macs with less than 128 GB of memory ## On Hugging Face, 13 November 2026 - Task: text generation - Library: mlx-serve - Parameters: 27.1B - Weights: about 109 GB in U32 - Formats: Safetensors - Downloads in the last 30 days: 606 - Likes: 4 - License: mit - Languages: en, zh - Based on: deepseek-ai/DeepSeek-V4.1-Flash-1017 - Tags: mlx-serve, safetensors, deepseek_v41, gptq, expert-pruning, engram, dspark, text-generation ## Links - Model: https://huggingface.co/ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw - Files: https://huggingface.co/ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw ``` 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 [ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw on Hugging Face](https://huggingface.co/ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw) ## 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 | | --- | --- | --- | --- | --- | --- | | DeepSeek-V4.1-Flash-1017 iQ-MLX Pruned192 2.25bpw (this page) | 606 | 4 | 27.1B | mit | 2026-11-05 | | [DeepSeek-V4.1-Flash-1017 TrellisMX K2 Mix](https://mindket.com/p/07ee61ca-5fd5-44fb-a019-f885468d68a4) | 338 | 12 | 115B | mit | 2026-10-20 | | [Raptor-0.6-4B-JANG\_6M](https://mindket.com/p/959efc07-1497-4bb0-a31c-13867e79912c) | 1,032 | 7 | 4.1B | apache-2.0 | 2026-09-28 | | [Qwen3.8-Whittle-MoE-27B-MLX-4bit](https://mindket.com/p/62c224d0-5cf9-4116-b0e4-4faeb9832a1a) | 1,611 | 11 | 26.9B | apache-2.0 | 2026-08-24 | | [DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF](https://mindket.com/p/1350113a-de6f-4d62-96d6-599c30da33a2) | 342,280 | 225 | 197B | mit | 2026-11-02 | | [GLM-5.3-Flash-Coder-RCO-152E-GGUF](https://mindket.com/p/3d3f2b43-1835-4865-a6e4-82126e543835) | 34,478 | 36 | 170B | mit | 2026-10-31 | 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: 2026-11-05 - First published: 2026-11-05 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw on Hugging Face](https://huggingface.co/ddalcu/DeepSeek-V4.1-Flash-1017-MLX-Serve-iQ-MLX-Pruned192-2.25bpw) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/5f45d8ea-67f6-4df8-b44f-d0e081f8e601) - [Its page on Mindket](https://mindket.com/p/5f45d8ea-67f6-4df8-b44f-d0e081f8e601)