Run DeepSeek V4 Flash Vision-Exp on M5 Max

Yes — DeepSeek V4 Flash Vision-Exp (305B-A13B) runs at 39 tok/s on M5 Max with 128 GB RAM using Q2_K quantization via llama.cpp. A capable open-source LLM with 305B-A13B parameters.

Speed
estimated39
tok/s
First Token
seconds
RAM Needed
128
GB minimum
Engine
llama.cpp
recommended
Want to run DeepSeek V4 Flash Vision-Exp faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates DeepSeek V4 Flash Vision-Exp 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 second39 tok/s
Time to first token
QuantizationQ2_K
Minimum RAM128 GB
Recommended enginellama.cpp
Parameters305B-A13B
Benchmark date2026-09

Q2_K 305B-A13B llama.cpp M5 Max

Setup Guide: Run DeepSeek V4 Flash Vision-Exp on M5 Max

The recommended engine for DeepSeek V4 Flash Vision-Exp on M5 Max is llama.cpp. Install Ollama, then pull the model:

ollama run deepseek-v4-flash-vision-exp

Ollama handles quantization automatically — it will download the Q2_K variant (~128 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Ultra 47 tok/s 256 GB llama.cpp
M4 Ultra 42 tok/s 192 GB llama.cpp
M3 Ultra 33 tok/s 256 GB llama.cpp

System Requirements

To run DeepSeek V4 Flash Vision-Exp on M5 Max you need:

🛒 Get a Mac that runs DeepSeek V4 Flash Vision-Exp

DeepSeek V4 Flash Vision-Exp 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 V4 Flash Vision-Exp stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard