llamaperf

Qwen3.6 35B (3B active)

on Intel Arc Pro B70 · llama.cpp · 262,000 ctx

Tone: positiveIntel hardware
Aug 28, 2026
Throughput
70.5 t/s gen · 977.4 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q4_K_M (GGUF)
KV cache
Q8

Use cases

coding

Summary

User reports creating a poker game without issues. User mentions trying Intel's vLLM fork previously.