Can I run it?
Can I run Kwaipilot KAT Coder V2.5 Dev on Apple M1 Max?
Tight fit
Tight fit fully in unified memory on your Apple M1 Max at Q5_K_S, 8K context, about 48–66 tok/s. Weights 22.5 GB plus 0.19 GB of KV cache — 23.2 GB of 24.0 GB usable. Up to 16K context still fits.
Best quantQ5_K_S
Working context8K
Max that fits16K
Speed48–66 tok/s
Weights22.5 GB
KV cache0.19 GB
Total23.2 GB
Usable24.0 GB
Kwaipilot KAT Coder V2.5 Dev details · Apple M1 Max page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:Q5_K_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 Q5_K_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%.
- Q5_K_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 M1 Max? — Tight fit, UD-Q4_K_XL, 105–143 tok/s
- Can I run Qwen3.8 35B A3B Distill on Apple M1 Max? — Tight fit, Q4_K_M, 110–150 tok/s
- Can I run Qwen3.5 35B A3B on Apple M1 Max? — Tight fit, UD-Q4_K_XL, 105–143 tok/s
Updated 2026-10-24. Profile on this page is the device default.