Arao AI
Back to search results

Qwen3.8-9B · IQ3_S

Start a discussion
NVIDIA H2097GBStrata v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_S) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

80.72 tok/s

Decode

Decode speed

287.96 tok/s

Prefill

Prefill speed

1.21 s

TTFT

Time to first token

14.57 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 · IQ3_S Decode 57.73 · Prefill 250.91 ·
  2. vLLM · Q3_K_L Decode 54.56 · Prefill 274.28 ·
  3. Strata · IQ3_S (current)Decode 80.72 · Prefill 287.96 ·
  4. Strata · Q3_K_M Decode 74.4 · Prefill 349.95 ·

Core figures

Decode (avg)
80.72 tok/s
Prefill (avg)
287.96 tok/s
TTFT (avg)
1.21 s
VRAM (avg)
14.57 GB
MTP acceptance rate
0.7
TTFB
0.65 GB
Power draw
340.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ3_S
Framework
Strata
Version
v0.28
Context length
8192 tokens
Batch size
512
GPU layers
8
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)
14.57 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.4
Power draw
340.6 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

    v0.28 · Windows 11 24H2 · CUDA 12.4 · 8192 ctx

    80.72 tok/s

    Decode

    287.96 tok/s

    Prefill

    1.21 s

    TTFT

    14.57 GB

    VRAM

    0.7

    MTP

    340.6 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=56 running model_id=52 at IQ3_S