Arao AI
Back to search results

Qwen3-1.7B · Q2_K

Start a discussion
NVIDIA RTX 409024GBStrata v0.51L2 Cross-framework verified

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

285.75 tok/s

Decode

Decode speed

1,116.76 tok/s

Prefill

Prefill speed

0.6 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 Decode 306.65 · Prefill 1436.24 ·
  3. Strata · IQ1_S Decode 287.87 · Prefill 1066.63 ·
  4. Strata · Q2_K (current)Decode 285.75 · Prefill 1116.76 ·

Core figures

Decode (avg)
285.75 tok/s
Prefill (avg)
1,116.76 tok/s
TTFT (avg)
0.6 s
VRAM (avg)
4.06 GB
MTP acceptance rate
0.63
TTFB
2.29 GB
Power draw
415.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q2_K
Framework
Strata
Version
v0.51
Context length
2048 tokens
Batch size
1024
GPU layers
12
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
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
415.2 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

    v0.51 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    285.75 tok/s

    Decode

    1,116.76 tok/s

    Prefill

    0.6 s

    TTFT

    4.06 GB

    VRAM

    0.63

    MTP

    415.2 W

    Power draw

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