llamaperf

Qwen3.6 35B (3B active)

on RTX 3070 Laptop 8GB · Krasis

Tone: positive
Sep 27, 2026
Throughput
12.5 t/s gen · 222.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
HQQ4
KV cache
k4v4
System RAM
32 GB
VRAM reported
8 GB

Summary

User reports Qwen3.6-35B-A3B at 12.48 t/s generation and 222 t/s prefill on a single RTX 3070 Laptop 8GB with 32GB system RAM. Setup is Krasis runtime with HQQ4 quantization and k4v4 KV cache, streaming the model from system RAM through VRAM. Figures are best throughput obtained during the benchmark, not averages. The post also lists results for RTX 5080, RTX A4500, and RTX 5090.