Can I run it?
Can I run Kwaipilot KAT Coder V2.5 Dev on Apple M3 Pro?
Runs
Runs fully in unified memory on your Apple M3 Pro at IQ2_S, 8K context, about 38–52 tok/s. Weights 10.3 GB plus 0.19 GB of KV cache — 10.8 GB of 13.0 GB usable. Up to 64K context still fits.
Best quantIQ2_S
Working context8K
Max that fits64K
Speed38–52 tok/s
Weights10.3 GB
KV cache0.19 GB
Total10.8 GB
Usable13.0 GB
Kwaipilot KAT Coder V2.5 Dev details · Apple M3 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:IQ2_S -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 IQ2_S
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%.
- IQ2_S 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 M3 Pro? — Tight fit, UD-Q2_K_XL, 67–91 tok/s
- Can I run Qwen3.5 35B A3B on Apple M3 Pro? — Tight fit, UD-IQ3_XXS, 68–93 tok/s
- Can I run Tiel Coder 35B A3B on Apple M3 Pro? — Tight fit, UD-Q2_K_XL, 67–91 tok/s
Updated 2026-10-24. Profile on this page is the device default.