Best Local LLMs for the Apple M3 Ultra

Written by Jakub Rusinowski · Last updated July 12, 2026

Best all-round pick: Qwen 3.5 397B

The Apple M3 Ultra has 512 GB of unified memory, of which about 384 GB is available to a model. The largest model it can hold is Qwen3-Coder 480B-A35B (MoE) (480B, 290.6 GB at Q4_K_M).

Best models overall on the Apple M3 Ultra

ModelScoreMemory at Q4_K_MContextLicence
Qwen 3.5 397B96.3240.5 GB125KApache 2.0
Qwen 3.5 397B-A17B95.9240.5 GB256KApache 2.0
GLM-6 355B-A32B95.4215.1 GB195KMIT
Llama 4 Maverick 17B95.3242.3 GB1MLlama Community
Qwen 3 235B-A22B (MoE)93.8142.7 GB125KApache 2.0
DeepSeek V4.1 Flash93.8172.3 GB977KMIT

Best model by what you are doing

WorkloadRecommended on this GPU
CodingQwen3-Coder 480B-A35B (MoE) (100)
GLM-6 355B-A32B (99.1)
DeepSeek V4.1 Flash (97.8)
General assistantQwen 3.5 397B (96.3)
Qwen 3.5 397B-A17B (95.9)
GLM-6 355B-A32B (95.4)
ReasoningQwen 3.5 397B (98.9)
Llama 4 Maverick 17B (98.2)
Qwen 3 235B-A22B (MoE) (98.1)
RAGDeepSeek V4.1 Flash (97.6)
DeepSeek V4-Flash (97.4)
Qwen 3.5 397B-A17B (94.9)
AgentsQwen3-Coder 480B-A35B (MoE) (97.2)
GLM-6 355B-A32B (94.6)
Ternary Bonsai 27B (87.8)
VisionQwen 3.5 397B (100)
MiniMax M3-VL (96.8)
Llama 3.2 90B Vision Instruct (91.5)

How these numbers are calculated

FAQ

What is the best LLM for the Apple M3 Ultra?

Qwen 3.5 397B is the strongest all-round pick that fits its 384 GB.

What is the largest model the Apple M3 Ultra can run?

Qwen3-Coder 480B-A35B (MoE) — 480B parameters, needing 290.6 GB at Q4_K_M.

How much of the Apple M3 Ultra's memory can a model actually use?

About 384 GB of its 512 GB, because macOS reserves a share of unified memory for the system.

Compatibility Checks for the Apple M3 Ultra

By Workload

More

← All GPUs | Apple M3 Ultra specs