Can I run it?
Can I run Kwaipilot KAT Coder V2.5 Dev on GeForce RTX 5090?
Runs
Runs fully on your GeForce RTX 5090 at Q5_K_M, 8K context, about 210–286 tok/s. Weights 23.3 GB plus 0.19 GB of KV cache — 24.0 GB of 29.9 GB usable. Up to 256K context still fits.
Best quantQ5_K_M
Working context8K
Max that fits256K
Speed210–286 tok/s
Weights23.3 GB
KV cache0.19 GB
Total24.0 GB
Usable29.9 GB
Kwaipilot KAT Coder V2.5 Dev details · GeForce RTX 5090 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:Q5_K_M -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_M
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_M size is the real GGUF file size from Hugging Face.
- 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
- 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 GeForce RTX 5090? — Tight fit, UD-Q6_K, 364–497 tok/s
- Can I run Qwen3.8 35B A3B Distill on GeForce RTX 5090? — Tight fit, Q6_K, 374–510 tok/s
- Can I run Qwen3.5 35B A3B on GeForce RTX 5090? — Tight fit, UD-Q6_K, 374–510 tok/s
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.