Can I run it?

Can I run Kwaipilot KAT Coder V2.5 Dev on Apple M4 Pro?

Tight fit

Tight fit fully in unified memory on your Apple M4 Pro at Q3_K_L, 8K context, about 47–63 tok/s. Weights 15.7 GB plus 0.19 GB of KV cache — 16.4 GB of 18.0 GB usable. Up to 64K context still fits.

Best quantQ3_K_L

Working context8K

Max that fits64K

Speed47–63 tok/s

Weights15.7 GB

KV cache0.19 GB

Total16.4 GB

Usable18.0 GB

Kwaipilot KAT Coder V2.5 Dev details · Apple M4 Pro page · How this estimate is made

Run commands

llama.cpp

llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:Q3_K_L -c 8192 -ngl 40

No matching name in the Ollama library snapshot.

LM Studio

lms get bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF
# Then load quant Q3_K_L

Assumptions

Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
Q3_K_L size is the real GGUF file size from Hugging Face.
Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

Can I run Qwen3.6 35B A3B on Apple M4 Pro? — Tight fit, UD-IQ4_XS, 88–120 tok/s
Can I run Qwen3.8 35B A3B Distill on Apple M4 Pro? — Tight fit, Q3_K_M, 90–123 tok/s
Can I run Qwen3.5 35B A3B on Apple M4 Pro? — Tight fit, UD-IQ4_XS, 89–122 tok/s

Updated 2026-10-24. Profile on this page is the device default.