Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ4_XS

Start a discussion
NVIDIA RTX 4070 Ti12GBvLLM v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ4_XS) on NVIDIA RTX 4070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

254.8 tok/s

Decode

Decode speed

1,153.22 tok/s

Prefill

Prefill speed

1.63 s

TTFT

Time to first token

2.88 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 · IQ3_S Decode 273.48 · Prefill 1262.92 ·
  2. vLLM · IQ4_XS (current)Decode 254.8 · Prefill 1153.22 ·
  3. Ollama · Q3_K_S Decode 265.74 · Prefill 1442.65 ·
  4. Ollama · Q8_0 Decode 145.11 · Prefill 753.08 ·

Core figures

Decode (avg)
254.8 tok/s
Prefill (avg)
1,153.22 tok/s
TTFT (avg)
1.63 s
VRAM (avg)
2.88 GB
MTP acceptance rate
—
TTFB
2.04 GB
Power draw
260.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ4_XS
Framework
vLLM
Version
v0.26
Context length
2048 tokens
Batch size
32
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 Ti
Nominal VRAM
12 GB
Measured VRAM (avg)
2.88 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.8
Power draw
260.2 W

Sources & evidence

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

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

    v0.26 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    254.8 tok/s

    Decode

    1,153.22 tok/s

    Prefill

    1.63 s

    TTFT

    2.88 GB

    VRAM

    —

    MTP

    260.2 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=42 running model_id=59 at IQ4_XS