Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| native 4-bit | 595 GB | 643 GB | more than any Mac |
| 3-bit lower quality | 438 GB | 473 GB | more than any Mac |
| 2-bit lower quality | 313 GB | 338 GB | 512 GB |
Ships in a native low-bit format: about 595 GB of weights.
On every Apple chip
The smallest memory size of each chip that runs Kimi K2.7 Code, 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 | 2-bit Runs well | 54–96 |
| 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 | 2-bit Runs well | 37–66 |
| 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 Kimi K2.7 Code, 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/Kimi-K2.7-Code-4bitBuild: mlx-community/Kimi-K2.7-Code-4bit 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 Kimi K2.7 Code
| Made by | Moonshot AI |
|---|---|
| Parameters | 1,000B total · 32B active (mixture of experts) |
| Context | 256K tokens |
| Licence | Modified MIT |
| Released | 2026-06 |
| Input | Text and images |
| Intelligence | 25.8 on the Artificial Analysis Intelligence Index |
| Weights | moonshotai/Kimi-K2.7-Code |
Questions
- How much memory does Kimi K2.7 Code need?
- About 595 GB of weights at native 4-bit, plus room for the context: 643 GB in all. That is more than any Mac has today.
- How fast is Kimi K2.7 Code on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 54–96 tokens a second (2-bit). The smallest Mac that runs it, with 512 GB, manages about 54–96 on an M5 Ultra.
- Why does Kimi K2.7 Code run faster than its size suggests?
- It is a mixture-of-experts model: it holds 1,000B parameters in memory but reads only 32B 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 Kimi K2.7 Code well and links here.
[](https://mlx.app/run/kimi-k2.7-code)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.