Can I run it?
Can I run Qwen3.8 27B on Intel Arc B580?
Tight fit
Tight fit fully on your Intel Arc B580 at UD-Q2_K_XL, 8K context, about 24–33 tok/s. Weights 9.15 GB plus 0.57 GB of KV cache — 10.1 GB of 10.9 GB usable. Up to 16K context still fits.
Best quantUD-Q2_K_XL
Working context8K
Max that fits16K
Speed24–33 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights9.15 GB
KV cache0.57 GB
Total10.1 GB
Usable10.9 GB
Qwen3.8 27B details · Intel Arc B580 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.8-27B-GGUF:UD-Q2_K_XL -c 8192 -ngl 64
Ollama
ollama run qwen3.8
LM Studio
lms get unsloth/Qwen3.8-27B-GGUF # Then load quant UD-Q2_K_XL
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%.
- UD-Q2_K_XL 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 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)
- Can I run Qwen2.5 32B Instruct on Intel Arc B580? — Heavily degraded, IQ2_XXS, 25–34 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.