llamaperf

Qwen3.6 35B (3B active)

on NVIDIA RTX 3060 12GB · Strata

Tone: positiveNVIDIA hardware
Nov 6, 2026
Throughput
106.0 t/s gen
Quant
Q2_K_XL (GGUF)
VRAM reported
12 GB

Summary

User reports Qwen3.6-35B-A3B at 106 tok/s for a single user on one 12 GB RTX 3060, served by Strata. Setup is Strata with a Q2_K_XL GGUF and --parallel 4; the 35B MoE is quantized to fit the 12 GB card. Aggregate throughput rises to 139 tok/s with 2 users (69 tok/s each) and 164 tok/s with 4 users (41 tok/s each). The server exposes OpenAI and Anthropic APIs, per-key usage logs and a fair queue.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.6 35B · 3B active at 4-bit by hardware

Bars are medians on one scale, 0 to 215.1 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the NVIDIA RTX 3060 12GB

Bars are medians on one scale, 0 to 113.6 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA RTX 3060 12GB →Every Qwen3.6 report →Estimate Qwen3.6 on this card →