Yes — KAT-Coder-V2.5 (35B-A3B) runs at 24 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.4s. A capable open-source LLM with 35B-A3B parameters.
Want to run KAT-Coder-V2.5 faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates KAT-Coder-V2.5 on M4 Pro 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 | 24 tok/s |
| Time to first token | 0.4s |
| Quantization | Q4_K_M |
| Minimum RAM | 24 GB |
| Recommended engine | Ollama |
| Parameters | 35B-A3B |
| Benchmark date | 2026-08 |
Q4_K_M 35B-A3B Ollama M4 Pro
The recommended engine for KAT-Coder-V2.5 on M4 Pro is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 52 tok/s | 0.3s | 64 GB | MLX |
| M4 Max | 47 tok/s | 0.3s | 48 GB | MLX |
To run KAT-Coder-V2.5 on M4 Pro you need:
KAT-Coder-V2.5 needs about 24 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 KAT-Coder-V2.5 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard