Apple M3 Max for local LLMs
Written by Jakub Rusinowski · Last updated
With 128 GB at 400 GB/s, the M3 Max runs 139 catalogued models at Q4_K_M with 8K context. The largest that fits is Mistral Medium 3.5 128B (~80.9 GB), and the top pick is Qwen 3.5 122B-A10B at 15–31 tok/s.
Up to 128 GB unified memory, enough for 70B-class models at Q4_K_M. Very popular among AI developers. Available as MacBook Pro or Mac Studio.
Models that run on the M3 Max
Q4_K_M, 8K context, 96 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 96 GB | VRAM | Speed |
|---|---|---|---|
| Qwen 3.5 122B-A10B Qwen 3.5 | 74.5 GB | 15–31 tok/s | |
| Nemotron 3 Super 120B-A12B Nemotron 3 Super | 73.3 GB | 13–28 tok/s | |
| GPT-OSS 120B GPT-OSS | 71.9 GB | 33–68 tok/s | |
| Llama 4 Scout 17B Llama 4 | 68.2 GB | 11–24 tok/s | |
| Llama 4.5 Scout Llama 4.5 | 66.6 GB | 10–22 tok/s | |
| Qwen3-Coder-Next (80B-A3B MoE) Qwen3-Coder | 49.1 GB | 29–60 tok/s | |
| Kolibri 1 Kolibri | 48.4 GB | 49–102 tok/s | |
| Nemotron 3.5 Bolt 74B Nemotron 3.5 | 45.6 GB | 23–48 tok/s | |
| K2 Horizon MoVA 36B-A4B K2 Horizon | 25 GB | 30–63 tok/s | |
| Qwen 3.6 35B-A3B Qwen 3.6 | 22.1 GB | 54–112 tok/s | |
| Nex-N2.5 mini Nex-N2.5 | 21.9 GB | 33–68 tok/s | |
| Nex-N2 mini Nex-N2 | 21.9 GB | 33–68 tok/s |
Buy it or rent the same memory
Buy the card, or rent a GPU with the same memory by the hour to try models first.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Speed vs other GPUs
Llama 3.1 8B, Q4_K_M. Estimated ranges. How this is calculated
Specifications
Specs last updated 2026-09-29.
- Memory
- 128 GB
- Memory bandwidth
- 400 GB/s
- Architecture
- ARM, 3nm TSMC
- Series
- Apple Silicon
- Board power
- 35 W
- Release year
- 2023
- Usable for models
- 96 GB (~75% of unified)
Similar GPUs
Frequently asked questions
Can the Apple M3 Max run local LLMs?
Yes. With 128 GB (96 GB usable by a model) it runs 139 of the catalogued models at Q4_K_M with 8K context; the largest is Mistral Medium 3.5 128B, needing about 80.9 GB.
How fast is the Apple M3 Max for AI inference?
It is estimated to run Llama 3.1 8B at 24–49 tok/s at Q4_K_M. Llama 3.3 70B is estimated at 3.2–6.7 tok/s. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 128 GB?
Among the best that fit: Qwen 3.5 122B-A10B, Nemotron 3 Super 120B-A12B, GPT-OSS 120B, Llama 4 Scout 17B, Llama 4.5 Scout. The quickest start is Ollama: ollama run llama3.3:70b.
Keep going
Can I run it on the M3 Max?
More for this card
Tools