Run DeepSeek R1 32B on M3 Max

Yes — DeepSeek R1 32B (32B) runs at 14 tok/s on M3 Max with 36 GB RAM using Q4_K_M quantization via Ollama. First token latency is 2.0s. DeepSeek's 32B reasoning model delivering frontier-grade results locally.

Speed
14
tok/s
First Token
2.0
seconds
RAM Needed
36
GB minimum
Engine
Ollama
recommended
Want to run DeepSeek R1 32B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates DeepSeek R1 32B on M3 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 second14 tok/s
Time to first token2.0s
QuantizationQ4_K_M
Minimum RAM36 GB
Recommended engineOllama
Parameters32B
Benchmark date2025-12

Q4_K_M 32B Ollama M3 Max

Setup Guide: Run DeepSeek R1 32B on M3 Max

The recommended engine for DeepSeek R1 32B on M3 Max is Ollama. Install Ollama, then pull the model:

ollama run deepseek-r1:32b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~36 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 27 tok/s 1.2s 64 GB Ollama
M4 Max 18 tok/s 1.8s 48 GB LM Studio

System Requirements

To run DeepSeek R1 32B on M3 Max you need:

🛒 Get a Mac that runs DeepSeek R1 32B

DeepSeek R1 32B needs about 36 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 32B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard