Arao AI
Back to search results

Qwen3.5-4B · IQ4_XS

Start a discussion
NVIDIA H2097GBStrata v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ4_XS) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

97.77 tok/s

Decode

Decode speed

362.6 tok/s

Prefill

Prefill speed

2.45 s

TTFT

Time to first token

8.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q3_K_S Decode 84.6 · Prefill 335.18 ·
  2. vLLM · Q4_K_M Decode 68.71 · Prefill 315.97 ·
  3. Strata · IQ4_XS (current)Decode 97.77 · Prefill 362.6 ·

Core figures

Decode (avg)
97.77 tok/s
Prefill (avg)
362.6 tok/s
TTFT (avg)
2.45 s
VRAM (avg)
8.32 GB
MTP acceptance rate
0.7
TTFB
0.78 GB
Power draw
313.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ4_XS
Framework
Strata
Version
v0.31
Context length
8192 tokens
Batch size
1024
GPU layers
12
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)
8.32 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
313.1 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

    v0.31 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx

    97.77 tok/s

    Decode

    362.6 tok/s

    Prefill

    2.45 s

    TTFT

    8.32 GB

    VRAM

    0.7

    MTP

    313.1 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=56 running model_id=48 at IQ4_XS