Arao AI
Back to search results

Qwen3-1.7B · Q2_K

Start a discussion
NVIDIA RTX 409024GBllama.cpp v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q2_K) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

306.65 tok/s

Decode

Decode speed

1,436.24 tok/s

Prefill

Prefill speed

1.31 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 · IQ2_M Decode 323.97 · Prefill 1188.09 ·
  2. llama.cpp · Q2_K (current)Decode 306.65 · Prefill 1436.24 ·
  3. Strata · IQ1_S Decode 287.87 · Prefill 1066.63 ·
  4. Strata · Q2_K Decode 285.75 · Prefill 1116.76 ·

Core figures

Decode (avg)
306.65 tok/s
Prefill (avg)
1,436.24 tok/s
TTFT (avg)
1.31 s
VRAM (avg)
4.06 GB
MTP acceptance rate
—
TTFB
2.45 GB
Power draw
479.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.52
Context length
8192 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
4.06 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
479.7 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

    v0.52 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    306.65 tok/s

    Decode

    1,436.24 tok/s

    Prefill

    1.31 s

    TTFT

    4.06 GB

    VRAM

    —

    MTP

    479.7 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=1 running model_id=55 at Q2_K