Yes — DeepSeek R1 8B (8B) runs at 58 tok/s on M2 with 16 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.8s. DeepSeek's MIT-licensed 8B reasoning model with chain-of-thought thinking.
Want to run DeepSeek R1 8B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates DeepSeek R1 8B on M2 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 →
| Metric | Value |
|---|---|
| Tokens per second | 58 tok/s |
| Time to first token | 0.8s |
| Quantization | Q4_K_M |
| Minimum RAM | 16 GB |
| Recommended engine | Ollama |
| Parameters | 8B |
| Benchmark date | 2026-01 |
Q4_K_M 8B Ollama M2
The recommended engine for DeepSeek R1 8B on M2 is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~16 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 97 tok/s | 0.5s | 64 GB | Ollama |
| M4 | 78 tok/s | 0.5s | 16 GB | MLX |
| M1 | 38 tok/s | 1.2s | 16 GB | Ollama |
To run DeepSeek R1 8B on M2 you need:
DeepSeek R1 8B needs about 16 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.
See how DeepSeek R1 8B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard