Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 587 GB | 633 GB | more than any Mac |
| 6-bit | 449 GB | 484 GB | more than any Mac |
| 4-bit | 311 GB | 335 GB | 512 GB |
| 3-bit lower quality | 242 GB | 261 GB | 512 GB |
| 2-bit lower quality | 173 GB | 186 GB | 256 GB |
Plus about 203 GB of Engram lookup tables, not counted here: runtimes such as DwarfStar leave them on the SSD, while MLX builds load them into memory too.
On every Apple chip
The smallest memory size of each chip that runs DeepSeek V4.1 Flash 1017, the best version that fits it, and the writing speed you can expect.
| Chip | Needs | Version | Tokens/s |
|---|---|---|---|
| M6 | no size fits | Too big | – |
| M5 Ultra | 512 GB | 4-bit Runs well | 60–107 |
| M5 Max | no size fits | Too big | – |
| M5 Pro | no size fits | Too big | – |
| M5 | no size fits | Too big | – |
| M4 Max | no size fits | Too big | – |
| M4 Pro | no size fits | Too big | – |
| M4 | no size fits | Too big | – |
| M3 Ultra | 512 GB | 4-bit Runs well | 41–73 |
| M3 Max | no size fits | Too big | – |
| M3 Pro | no size fits | Too big | – |
| M3 | no size fits | Too big | – |
| M2 Ultra | no size fits | Too big | – |
| M2 Max | no size fits | Too big | – |
| M2 Pro | no size fits | Too big | – |
| M2 | no size fits | Too big | – |
| M1 Ultra | no size fits | Too big | – |
| M1 Max | no size fits | Too big | – |
| M1 Pro | no size fits | Too big | – |
| M1 | no size fits | Too big | – |
How to run it
- The easy way: download MLX Harness, free and open source. Search for DeepSeek V4.1 Flash 1017, download the version that fits your Mac, and chat. It also serves the model to your other apps over an OpenAI-compatible API.Download MLX HarnessFree · Apple Silicon · macOS 14.5 or later
- In Terminal with Apple’s MLX:
pip install mlx-lmmlx_lm.chat --model mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtpBuild: mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp on Hugging Face. Other precisions sit next to it.
Step by step: download and run LLMs on a Mac · how to use MLX Harness · MLX vs Ollama vs llama.cpp
About DeepSeek V4.1 Flash 1017
| Made by | DeepSeek |
|---|---|
| Parameters | 552B total · 16B active (mixture of experts) |
| Context | 1M tokens |
| Licence | MIT |
| Released | 2026-10 |
| Input | Text and images |
| Intelligence | 45.1 on the Artificial Analysis Intelligence Index |
| Weights | deepseek-ai/DeepSeek-V4.1-Flash-1017 |
Guide: step by step on mlx.app
Questions
- How much memory does DeepSeek V4.1 Flash 1017 need?
- About 311 GB of weights at 4-bit, plus room for the context: 335 GB in all. On a Mac that means 512 GB of unified memory or more, since macOS lets the GPU use about 75% of it by default.
- How fast is DeepSeek V4.1 Flash 1017 on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 60–107 tokens a second (4-bit). The smallest Mac that runs it, with 512 GB, manages about 60–107 on an M5 Ultra.
- Why does DeepSeek V4.1 Flash 1017 run faster than its size suggests?
- It is a mixture-of-experts model: it holds 552B parameters in memory but reads only 16B for each token, so it writes at the speed of a much smaller model.
Similar models
For your model card or README
Shows the smallest Mac that runs DeepSeek V4.1 Flash 1017 well and links here.
[](https://mlx.app/run/deepseek-v4.1-flash-1017)How it’s worked out
Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.