Arao AI
Back to search results

Qwen3-1.7B · Q2_K

Start a discussion
NVIDIA RTX 3060 12GB12GBllama.cpp v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q2_K) on NVIDIA RTX 3060 12GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

169.7 tok/s

Decode

Decode speed

583.54 tok/s

Prefill

Prefill speed

1.99 s

TTFT

Time to first token

4.06 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q2_K (current)Decode 169.7 · Prefill 583.54 ·
  2. vLLM · Q3_K_L Decode 134.55 · Prefill 711.57 ·
  3. vLLM · Q8_0 Decode 84.49 · Prefill 329.46 ·

Core figures

Decode (avg)
169.7 tok/s
Prefill (avg)
583.54 tok/s
TTFT (avg)
1.99 s
VRAM (avg)
4.06 GB
MTP acceptance rate
—
TTFB
1.36 GB
Power draw
278.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.54
Context length
8192 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
4.06 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.4
Power draw
278.6 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.54 · Windows 11 23H2 · CUDA 12.4 · 8192 ctx

    169.7 tok/s

    Decode

    583.54 tok/s

    Prefill

    1.99 s

    TTFT

    4.06 GB

    VRAM

    —

    MTP

    278.6 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=15 running model_id=55 at Q2_K