Arao AI
Back to search results

Qwen3-1.7B · Q2_K

Start a discussion
NVIDIA RTX 407012GBvLLM v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q2_K) on NVIDIA RTX 4070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

180.64 tok/s

Decode

Decode speed

850.28 tok/s

Prefill

Prefill speed

2.21 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

5 days ago

Last verified

Performance

  1. vLLM · Q2_K (current)Decode 180.64 · Prefill 850.28 ·

Core figures

Decode (avg)
180.64 tok/s
Prefill (avg)
850.28 tok/s
TTFT (avg)
2.21 s
VRAM (avg)
4.06 GB
MTP acceptance rate
—
TTFB
1.45 GB
Power draw
199.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q2_K
Framework
vLLM
Version
v0.28
Context length
2048 tokens
Batch size
16
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4070
Nominal VRAM
12 GB
Measured VRAM (avg)
4.06 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
199.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.28 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    180.64 tok/s

    Decode

    850.28 tok/s

    Prefill

    2.21 s

    TTFT

    4.06 GB

    VRAM

    —

    MTP

    199.6 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=45 running model_id=55 at Q2_K