Can I run it?
Can I run Qwen3.5 4B on Intel Arc B580?
Runs
Runs fully on your Intel Arc B580 at BF16, 8K context, about 29–39 tok/s. Weights 7.85 GB plus 0.27 GB of KV cache — 8.50 GB of 10.9 GB usable. Up to 64K context still fits.
Best quantBF16
Working context8K
Max that fits64K
Speed29–39 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights7.85 GB
KV cache0.27 GB
Total8.50 GB
Usable10.9 GB
Qwen3.5 4B details · Intel Arc B580 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.5-4B-GGUF:BF16 -c 8192 -ngl 32
Ollama
ollama run qwen3.5
LM Studio
lms get unsloth/Qwen3.5-4B-GGUF # Then load quant BF16
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%.
- BF16 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 Qwen3.8 27B on Intel Arc B580? — Tight fit, UD-Q2_K_XL, 24–33 tok/s (estimate)
- Can I run gemma 4 12b it on Intel Arc B580? — Tight fit, Q6_K, 19–26 tok/s (estimate)
- Can I run Qwen3.5 9B on Intel Arc B580? — Tight fit, Q8_0, 26–35 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.