Can I run it?
Can I run Kwaipilot KAT Coder V2.5 Dev on Intel Arc B580?
Heavily degraded
Heavily degraded fully on your Intel Arc B580 at IQ2_XXS, 8K context, about 60–82 tok/s. Weights 9.11 GB plus 0.19 GB of KV cache — 9.68 GB of 10.9 GB usable. Up to 32K context still fits.
Best quantIQ2_XXS
Working context8K
Max that fits32K
Speed60–82 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights9.11 GB
KV cache0.19 GB
Total9.68 GB
Usable10.9 GB
Kwaipilot KAT Coder V2.5 Dev details · Intel Arc B580 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF:IQ2_XXS -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 IQ2_XXS
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- 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%.
- IQ2_XXS 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.
- This quant is IQ1 or IQ2. It can load, but quality is heavily degraded, so it is left off best-fit lists.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on Intel Arc B580? — Heavily degraded, UD-IQ2_XXS, 55–75 tok/s (estimate)
- Can I run Qwen3.5 35B A3B on Intel Arc B580? — Heavily degraded, UD-IQ2_XXS, 56–76 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.