M3 generation

Local LLMs on the M3 Ultra

The M3 Ultra moves 819 GB/s and takes up to 512 GB of unified memory. That combination runs everything up to DeepSeek V3 at Q4, at roughly 29.6 tokens/sec. Bandwidth sets the speed, memory sets the ceiling, and the tables below give both for every model.

Worth knowing. 512 GB was the first configuration able to hold a 671B MoE in memory.

Memory bandwidth

819 GB/s

Unified memory

96, 256, 512 GB

8B model at Q4

~97 tok/s

Found in: Mac Studio (2025). Specifications verified 2026-09-11against Apple’s published figures.

What the M3 Ultra runs, at Q4_K_M

Memory figures include a 3 GB reserve for macOS and an 8K context. Speeds come from a model fitted to our own measured benchmarks; the method and its error bars are on the calculator page.

ModelNeeds96 GB256 GB512 GB
Llama 3.2 3B8 GB154 tok/s154 tok/s154 tok/s
Mistral 7B16 GB103 tok/s103 tok/s103 tok/s
Qwen 2.5 7B16 GB100 tok/s100 tok/s100 tok/s
Llama 3.1 8B16 GB97 tok/s97 tok/s97 tok/s
DeepSeek R1 Distill 8B16 GB97 tok/s97 tok/s97 tok/s
Qwen 2.5 14B16 GB63 tok/s63 tok/s63 tok/s
Qwen 2.5 32B32 GB32.9 tok/s32.9 tok/s32.9 tok/s
Llama 3.3 70B56 GB16.4 tok/s16.4 tok/s16.4 tok/s
Qwen 2.5 72B56 GB15.9 tok/s15.9 tok/s15.9 tok/s
Mistral Large 296 GB9.7 tok/s9.7 tok/s9.7 tok/s
Llama 3.1 405B288 GB3 tok/s
DeepSeek V3480 GB29.6 tok/s

M3 Ultra against the M2 Ultra

Bandwidth went from 800 GB/s to 819 GB/s, which is 1.02x, and that ratio carries almost directly into generation speed at the same model and quantization. The memory ceiling went from 192 GB to 512 GB, which is the part that decides whether a model runs at all rather than how fast. That extra headroom is the stronger reason to upgrade, because speed you can wait out and memory you cannot.

Common questions

What is the largest model an M3 Ultra can run?

At Q4_K_M with 512 GB of unified memory, DeepSeek V3 is the largest of the major open models that fits, needing about 480 GB once macOS is accounted for. Anything larger has to drop to a smaller quantization, run across clustered machines, or move to a chip with a higher memory ceiling.

How fast is the M3 Ultra for local inference?

It has 819 GB/s of memory bandwidth, and generation speed on Apple Silicon is set almost entirely by bandwidth divided by the size of the weights. In practice that works out to roughly 97 tokens/sec on an 8B model at Q4 and 32.9 on a 32B, assuming they fit. That is about 1.02x the M2 Ultra at the same model size.

How much memory should I order with an M3 Ultra?

Memory decides which models you can run at all, and it cannot be upgraded later, so it is the one specification worth overbuying. M3 Ultra ships in 96, 256, 512 GB. The 96 GB configuration caps you at the small end; 512 GB is what opens up the larger models in the table on this page.

Rent an M3 Ultra instead of buying one

We run this exact chip as a dedicated machine, from $571/mo, with Ollama installed and an OpenAI compatible endpoint already exposed. Same silicon and the same numbers as this page, without the hosting, the static IP, or being your own on call.

Other Apple Silicon