Arao AI
Back to search results

Qwen3.5-27B · IQ2_XS

Start a discussion
NVIDIA H2097GBvLLM v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ2_XS) on NVIDIA H20 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

63.17 tok/s

Decode

Decode speed

260.61 tok/s

Prefill

Prefill speed

2.16 s

TTFT

Time to first token

29.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. vLLM · IQ2_XS (current)Decode 63.17 · Prefill 260.61 ·
  2. vLLM · Q8_0 Decode 27.55 · Prefill 97.34 ·
  3. Strata · IQ3_S Decode 67.46 · Prefill 225.71 ·

Core figures

Decode (avg)
63.17 tok/s
Prefill (avg)
260.61 tok/s
TTFT (avg)
2.16 s
VRAM (avg)
29.32 GB
MTP acceptance rate
—
TTFB
0.51 GB
Power draw
351.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ2_XS
Framework
vLLM
Version
v0.48
Context length
32768 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

Hardware

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

GPU
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
29.32 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
351.2 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.48 · Windows 11 23H2 · CUDA 12.8 · 32768 ctx

    63.17 tok/s

    Decode

    260.61 tok/s

    Prefill

    2.16 s

    TTFT

    29.32 GB

    VRAM

    —

    MTP

    351.2 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=56 running model_id=50 at IQ2_XS