Run DeepSeek R1 70B on M5 Max

Yes — DeepSeek R1 70B (70B) runs at 11 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 3.0s. DeepSeek's full 70B reasoning distillation — requires 64 GB+ Mac.

Speed
11
tok/s
First Token
3.0
seconds
RAM Needed
128
GB minimum
Engine
Ollama
recommended
Want to run DeepSeek R1 70B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates DeepSeek R1 70B on M5 Max using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second11 tok/s
Time to first token3.0s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineOllama
Parameters70B
Benchmark date2026-03

Q4_K_M 70B Ollama M5 Max

Setup Guide: Run DeepSeek R1 70B on M5 Max

The recommended engine for DeepSeek R1 70B on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run deepseek-r1:70b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~128 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 16 tok/s 2.2s 192 GB MLX

System Requirements

To run DeepSeek R1 70B on M5 Max you need:

🛒 Get a Mac that runs DeepSeek R1 70B

DeepSeek R1 70B needs about 128 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how DeepSeek R1 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard