Can I run it?
Can I run Kwaipilot KAT Coder V2.5 Dev on NVIDIA H100 SXM 80GB?
Tight fit
Tight fit fully on your NVIDIA H100 SXM 80GB at BF16, 8K context, about 145–197 tok/s. Weights 64.6 GB plus 0.19 GB of KV cache — 65.7 GB of 76.0 GB usable. Up to 256K context still fits.
Best quantBF16
Working context8K
Max that fits256K
Speed145–197 tok/s
Weights64.6 GB
KV cache0.19 GB
Total65.7 GB
Usable76.0 GB
Kwaipilot KAT Coder V2.5 Dev details · NVIDIA H100 SXM 80GB page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:BF16 -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 BF16
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%.
- BF16 size is the real GGUF file size from Hugging Face.
- CPU runs keep about 4 GB plus a 10% cushion 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 NVIDIA H100 SXM 80GB? — Tight fit, BF16, 299–407 tok/s
- Can I run Qwen3.8 35B A3B Distill on NVIDIA H100 SXM 80GB? — Tight fit, BF16, 298–407 tok/s
- Can I run Qwen3.8 Flash Next on NVIDIA H100 SXM 80GB? — Tight fit, UD-IQ1_M, 144–196 tok/s
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.