Can I run it?

Can I run Kwaipilot KAT Coder V2.5 Dev on Radeon RX 7900 XTX?

Tight fit

Tight fit fully on your Radeon RX 7900 XTX at Q4_K_M, 8K context, about 131–178 tok/s. Weights 19.9 GB plus 0.19 GB of KV cache — 20.6 GB of 22.3 GB usable. Up to 64K context still fits.

Best quantQ4_K_M

Working context8K

Max that fits64K

Speed131–178 tok/s

Weights19.9 GB

KV cache0.19 GB

Total20.6 GB

Usable22.3 GB

Kwaipilot KAT Coder V2.5 Dev details · Radeon RX 7900 XTX page · How this estimate is made

Run commands

llama.cpp

llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:Q4_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 Q4_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%.
Q4_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 Radeon RX 7900 XTX? — Tight fit, UD-Q4_K_XL, 251–342 tok/s
Can I run Qwen3.8 35B A3B Distill on Radeon RX 7900 XTX? — Tight fit, Q4_K_M, 264–360 tok/s
Can I run Qwen3.5 35B A3B on Radeon RX 7900 XTX? — Tight fit, UD-Q4_K_XL, 252–344 tok/s

Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.