Qwen3.8 27B
on Intel Arc Pro B70 · vLLM · 262,144 ctx
Oct 8, 2026
Use cases
codinglong-contextagentic
Summary
User reports Qwen3.8-27B EXL3 4.00bpw at 91.2 t/s decode (C1, prose) on one Intel Arc Pro B70 32GB.
Setup is vLLM 0.26.1 XPU with EXL3 trellis quantization, fp8 KV cache, 262,144 context, MTP speculative decoding k=3, int8 prefill and oneDNN fused attention.
Aggregate throughput scales to 365.2 t/s at C16; cold prefill is 2,421 t/s at 4K and 911 t/s at 254K. The same card with tuned llama.cpp SYCL Q4_K_M reaches 25.0 t/s at C1 and 999 t/s prefill at 4K.