What runs at each memory size
16–24 GB: models of 4–8 billion parameters in 4-bit quantization, an assistant for text and code, 5 GB per model. 36–48 GB: models of 20–35 billion, including a large Russian bank’s open 32-billion model, and at 48 GB a vision model next to it. 64 GB: 70-billion models in 4 bits with a short context. 128 GB: 70 billion with a long context, several models at once, and models with few active parameters at 35–120 billion. The personal agent of a bank’s IT director lives on a Mac, on a 35-billion model with 3 billion active parameters, at 70 tokens per second.
Speed
By the llama.cpp community table, on a 7-billion model in 4 bits: M4 Pro 50.7 tokens per second, M4 Max 83.1, M5 Max 119.9; prompt processing is 3,220 tokens per second on the M5 Max and 886 on the M4 Max. For a chat or an agent on a laptop, this is more than enough; the laptop’s limits are heat and battery under hours of load.
Price as of 29 September 2026
MacBook Pro 14 M5 Max, 128 GB of memory, 2 TB: $8,100 at a Russian seller, in stock. Configurations with 48 and 64 GB cost less; check the seller’s prices on the day you buy. For comparison: one 32 GB graphics card costs $9,000 without a computer (30 September 2026), and a Mac Studio M4 Max with 128 GB costs $11,000.
Software
LM Studio and Ollama install a model in minutes and give you a local API that works with common libraries; agents connect to it as they would to the cloud. This is how the personal agent from the bank case and a cloud provider’s agent work. Several users need a server and a batch serving engine.
Limits of a laptop
One user, not a service for a department. Long documents process more slowly than on a server card. The laptop leaves with the employee, together with the model and the data, so disk encryption is a must. For a team, the next step is a Mac Studio or a server with a graphics card.