Yes — DeepSeek V4 Flash (284B-A13B) runs at 30 tok/s on M3 Ultra with 256 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.5s. 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 Ultra 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 | 30 tok/s |
| Time to first token | 0.5s |
| Quantization | Q4_K_M |
| Minimum RAM | 256 GB |
| Recommended engine | MLX |
| Parameters | 284B-A13B |
| Benchmark date | 2026-08 |
Q4_K_M 284B-A13B MLX M3 Ultra
The recommended engine for DeepSeek V4 Flash on M3 Ultra is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run DeepSeek V4 Flash on M3 Ultra you need:
DeepSeek V4 Flash needs about 256 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