Yes — DeepSeek V4 Flash (284B-A13B) runs at 27 tok/s on M3 Max with 128 GB RAM using Q2_K quantization via MLX. First token latency is 0.6s. A capable open-source LLM with 284B-A13B parameters.
Want to run DeepSeek V4 Flash faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates DeepSeek V4 Flash 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 →
| Metric | Value |
|---|---|
| Tokens per second | 27 tok/s |
| Time to first token | 0.6s |
| Quantization | Q2_K |
| Minimum RAM | 128 GB |
| Recommended engine | MLX |
| Parameters | 284B-A13B |
| Benchmark date | 2026-08 |
Q2_K 284B-A13B MLX M3 Max
The recommended engine for DeepSeek V4 Flash on M3 Max is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M3 Ultra | 30 tok/s | 0.5s | 256 GB | MLX |
To run DeepSeek V4 Flash on M3 Max you need:
DeepSeek V4 Flash 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.
See how DeepSeek V4 Flash stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard