Arao AI
Back to search results

Qwen3-1.7B · Q3_K_L

Start a discussion
NVIDIA RTX 309024GBllama.cpp v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

227.45 tok/s

Decode

Decode speed

862.55 tok/s

Prefill

Prefill speed

0.46 s

TTFT

Time to first token

4.67 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_L (current)Decode 227.45 · Prefill 862.55 ·
  2. llama.cpp · Q5_K_S Decode 175.42 · Prefill 578.57 ·
  3. Strata · Q6_K Decode 215.56 · Prefill 902.66 ·

Core figures

Decode (avg)
227.45 tok/s
Prefill (avg)
862.55 tok/s
TTFT (avg)
0.46 s
VRAM (avg)
4.67 GB
MTP acceptance rate
—
TTFB
1.82 GB
Power draw
341.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_L
Framework
llama.cpp
Version
v0.31
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
4.67 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.6
Power draw
341.2 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

    v0.31 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx

    227.45 tok/s

    Decode

    862.55 tok/s

    Prefill

    0.46 s

    TTFT

    4.67 GB

    VRAM

    —

    MTP

    341.2 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=2 running model_id=55 at Q3_K_L