Can Inkling Small run on Mac Studio M5 Ultra 512GB?

YES — Runs great
Q4_K_M · 4K context · formula estimate

What this means

Inkling Small fits on the Mac Studio M5 Ultra · 512GB at Q4_K_M. We estimate it uses 190.7GB of the conservative 504GB working budget.

Estimated decode speed is 84.9118.9 tokens/s. A roughly 300-word answer may take around 4 seconds.

84.9–118.9tokens/s
estimated · instant
190.7GB
needed at Q4_K_M
Q4_K_M
quant selected
313.3GB
working headroom
needs 190.7 GBworking budget 504 GB
Apple M5 Ultra512 GB unified memoryMetalActive cooling

See how fast it feels

Using the midpoint of our 84.9118.9 tokens/s estimate for this demo.

Live demo · 101.9 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (162.5 GB) + mmap overhead170.6
KV cache4K context window19.3
RuntimemacOS inference app + compute buffers0.8
Total neededat Q4_K_M, 4K context190.7
Working budget512 GB unified memory − conservative macOS reserve504
Headroomremaining inside the working budget313.3

Pick your quant

QuantDownloadMemoryEstimated speedVerdict
IQ1_S74.8 GB98.7 GB~184.5–258.3 tok/s Runs great
Q3_K_M119.4 GB145.5 GB~115.6–161.8 tok/s Runs great
IQ4_XS127.4 GB153.9 GB~108.3–151.6 tok/s Runs great
Q4_K_S152.3 GB180 GB~90.6–126.9 tok/s Runs great
MXFP4158 GB186 GB~87.3–122.3 tok/s Runs great
Q4_K_M162.5 GB190.7 GB~84.9–118.9 tok/s Runs great
Q5_K_M196.1 GB226 GB~70.4–98.5 tok/s Runs great
Q6_K218.9 GB250 GB~63–88.3 tok/s Runs great
Q8_0280.3 GB314.4 GB~49.2–68.9 tok/s Runs great

Get it running on this Mac

Recommended app: LM Studio. Follow the point-and-click steps below.

1
Install LM Studio for Apple silicon.

Download LM Studio from its official site and drag it to Applications. Open it once and allow macOS to launch it. This route uses the graphical app; you do not need its CLI or local-server features.

2
Open Discover and paste the exact model repository.

Search for unsloth/Inkling-Small-GGUF. Use the publisher name shown on this page—or paste its full Hugging Face URL. Similarly named community uploads may contain different files.

3
Choose the Q4_K_M GGUF.

Open the GGUF download options and select the row containing Q4_K_M. The download should be about 162.5 GB. Do not select vision-projector or mmproj helper files for a text-only chat.

4
Download it, then open Chat and load that model.

Choose the downloaded model in the model selector and click Load if prompted. Keep the default local runtime and start with a 4K (4096-token) context. Close memory-heavy apps for the first load.

5
Send a simple first prompt.

Try “Explain why the sky is blue in three sentences.” This page estimates 84.9118.9 tokens/s; it is not an LM Studio measurement unless marked ✓ Verified.

6
Turn off Wi-Fi and ask again.

A second reply while offline confirms that the model is running on this Mac.

Why LM Studio?

This report names an exact Hugging Face repository and GGUF quant. LM Studio lets you search that exact source, choose the matching quant, download it, and chat without using Terminal.

Jan

An open-source GGUF alternative with friendly hardware-fit hints.

Its MLX engine is experimental, and support for new model architectures can lag.
Ollama

A trusted Ollama catalog model, or later use with coding tools and a local API.

An Ollama package may use different weights or a different quant from this report.
Msty

One interface for GGUF, MLX, Ollama, documents, and knowledge workflows.

It exposes more choices than the first-chat path and its free license is for personal use.
If it does not work
  • Model not listed: paste the exact repository unsloth/Inkling-Small-GGUF, not only the model nickname.
  • Download stalls: confirm there is enough free storage, reconnect to Wi-Fi, and restart the download inside the app.
  • Load fails or the app closes: quit memory-heavy apps. In LM Studio, confirm Q4_K_M is the model currently loaded. Otherwise use a smaller model from this Mac's results.
  • No reply while offline: make sure the downloaded local model—not a remote or cloud model—is selected in the chat.
Did the first offline reply work?

Your anonymous feedback helps us prioritize which Mac and model paths to retest.

Other models on this Mac

Inkling Small on other Mac Studio M5 Ultra configurations

FAQ

Can the Mac Studio M5 Ultra · 512GB run Inkling Small?

Yes at Q4_K_M. We estimate about 190.7GB of working memory and 84.9–118.9 tokens/s at 4K context.

Which Inkling Small quant should I use on this Mac?

Q4_K_M. It is a 162.5GB download and leaves about 313.3GB inside our conservative working budget.

Which app should I use for Inkling Small on this Mac?

Start with LM Studio. This page gives the complete point-and-click walkthrough.

Are these speeds measured on a Mac Studio M5 Ultra?

No. The range is a formula estimate based on memory bandwidth, model size, active parameters, cooling, and a 4K context. The app, backend, thermals, and prompt can change real performance.