Can I run it?

Can I run Kwaipilot KAT Coder V2.5 Dev on Apple M5 Max (40-core GPU)?

Tight fit

Tight fit fully in unified memory on your Apple M5 Max (40-core GPU) at Q8_0, 8K context, about 49–67 tok/s. Weights 34.4 GB plus 0.19 GB of KV cache — 35.2 GB of 36.0 GB usable.

Best quantQ8_0

Working context8K

Max that fits8K

Speed49–67 tok/s

Weights34.4 GB

KV cache0.19 GB

Total35.2 GB

Usable36.0 GB

Kwaipilot KAT Coder V2.5 Dev details · Apple M5 Max (40-core GPU) page · How this estimate is made

Run commands

llama.cpp

llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:Q8_0 -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 Q8_0

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%.
Q8_0 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 M5 Max (40-core GPU)? — Tight fit, Q8_0, 100–137 tok/s
Can I run Qwen3.8 35B A3B Distill on Apple M5 Max (40-core GPU)? — Runs, Q6_K, 128–175 tok/s
Can I run Qwen3.5 35B A3B on Apple M5 Max (40-core GPU)? — Tight fit, Q8_0, 100–137 tok/s

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