Best Local LLMs for the Mac Studio M5 Ultra (96 GB)

The best local LLM for a Mac Studio M5 Ultra (96 GB) is Qwen3.8-27B at 57 tok/s. With 96 GB of unified memory it runs 56 of the models we benchmark — from compact options up to 276B-class models. For everyday chat and coding, Qwen3.8-27B is the sweet spot. Full ranking below.

Unified memory
96
GB
Mem. bandwidth
1228
GB/s
Models that fit
56
of 81
Top speed
575
tok/s

Top 3 picks for the Mac Studio M5 Ultra (96 GB)

⭐ Best overall
27.8B · Apache 2.0 · cap 46/50
57 tok/s
⚡ Fastest
20B · MIT · cap 20/50
575 tok/s
🧠 Runner-up
276B · Apache 2.0 · cap 46/50
45 tok/s

Every model ranked for a Mac Studio M5 Ultra (96 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M5 Ultra). Click a model for its full benchmark and setup. All speeds are index estimates (memory-bandwidth model, cross-referenced with sourced benchmarks where available) — submit a real run →

#ModelSizeLicenseSpeedCapability
1Qwen3.8-27B27.8BApache 2.057 tok/s46/50
2KAT-Coder-V2.535BApache 2.0106 tok/s est.39/50
3Inkling-Small276BApache 2.045 tok/s46/50
4Qwen 3.6-27B27BApache 2.061 tok/s est.44/50
5Nemotron 3.5 Lightning30BOpenMDW123 tok/s est.36/50
6Qwen 3.6-35B-A3B35BApache 2.0106 tok/s est.38/50
7Laguna S 2.1118BOpenMDW53 tok/s43/50
8Muse Glimmer 30B30BApache 2.055 tok/s est.42/50
9Gemma 4 26B-A4B26BApache 2.098 tok/s est.35/50
10Laguna XS 2.133BOpenMDW113 tok/s est.33/50
11Gemma 4 31B31BApache 2.053 tok/s est.40/50
12Mistral Small 4119BApache 2.086 tok/s34/50

Showing the top 12 of 56 models that fit in 96 GB. See the full leaderboard or all benchmarks.

Quick start: run Qwen3.8-27B on your Mac Studio M5 Ultra

The fastest way to get started is Ollama. Install it, then pull the top pick for your Mac:

brew install ollama
ollama run qwen38-27b

Prefer a GUI? LM Studio gives you a one-click download and chat window. For step-by-step help see our Ollama install guide, or open the Qwen3.8-27B on M5 Ultra benchmark page for exact settings.

🛒 Get a Mac Studio M5 Ultra for local AI

The Mac Studio M5 Ultra (96 GB) comfortably runs 56 of the models we benchmark, led by Qwen3.8-27B. Grab one and start running LLMs offline today:

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.

FAQ: local LLMs on the Mac Studio M5 Ultra

What is the best local LLM for a Mac Studio M5 Ultra (96 GB)?

Qwen3.8-27B (27.8B, Apache 2.0) is the best all-round pick at 57 tok/s on the M5 Ultra. If you want maximum speed, Maple Preview 20B-A1B hits 575 tok/s; for maximum capability, Inkling-Small still fits in 96 GB.

How many models can a Mac Studio M5 Ultra with 96 GB run?

About 56 of the 81 models in the LLMCheck leaderboard fit in 96 GB of unified memory, from compact models up to Inkling-Small (276B).

Can a Mac Studio M5 Ultra run a 70B model?

Yes. A 70B model in Q4 quantization needs roughly 40–44 GB of memory, which fits in 96 GB with headroom for context.

Is 96 GB of RAM enough to run LLMs locally?

96 GB is plenty for local AI — you can run capable 30B–70B-class models. Because Apple Silicon uses unified memory, that figure is both your system RAM and your VRAM.

Related