Run KAT-Coder-V2.5 on M4 Max

Yes — KAT-Coder-V2.5 (35B-A3B) runs at 47 tok/s on M4 Max with 48 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.3s. A capable open-source LLM with 35B-A3B parameters.

Speed
47
tok/s
First Token
0.3
seconds
RAM Needed
48
GB minimum
Engine
MLX
recommended
Want to run KAT-Coder-V2.5 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates KAT-Coder-V2.5 on M4 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 second47 tok/s
Time to first token0.3s
QuantizationQ4_K_M
Minimum RAM48 GB
Recommended engineMLX
Parameters35B-A3B
Benchmark date2026-08

Q4_K_M 35B-A3B MLX M4 Max

Setup Guide: Run KAT-Coder-V2.5 on M4 Max

The recommended engine for KAT-Coder-V2.5 on M4 Max is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/kat-coder-v25-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run kat-coder-v25

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 52 tok/s 0.3s 64 GB MLX
M4 Pro 24 tok/s 0.4s 24 GB Ollama

System Requirements

To run KAT-Coder-V2.5 on M4 Max you need:

🛒 Get a Mac that runs KAT-Coder-V2.5

KAT-Coder-V2.5 needs about 48 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 KAT-Coder-V2.5 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard