Arao AI
Back to search results

gemma-4-31B-it · IQ3_XS

Start a discussion
NVIDIA H2097GBvLLM v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ3_XS) on NVIDIA H20 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

39.95 tok/s

Decode

Decode speed

179.27 tok/s

Prefill

Prefill speed

0.14 s

TTFT

Time to first token

42.46 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_XS (current)Decode 39.95 · Prefill 179.27 ·
  2. vLLM · Q4_K_S Decode 32.57 · Prefill 141.17 ·
  3. Ollama · Q8_0 Decode 18.96 · Prefill 65.76 ·

Core figures

Decode (avg)
39.95 tok/s
Prefill (avg)
179.27 tok/s
TTFT (avg)
0.14 s
VRAM (avg)
42.46 GB
MTP acceptance rate
—
TTFB
0.32 GB
Power draw
314.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ3_XS
Framework
vLLM
Version
v0.25
Context length
4096 tokens
Batch size
8
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 H20
Nominal VRAM
97 GB
Measured VRAM (avg)
42.46 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
12.6
Power draw
314.6 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

    v0.25 · Windows 11 24H2 · CUDA 12.6 · 4096 ctx

    39.95 tok/s

    Decode

    179.27 tok/s

    Prefill

    0.14 s

    TTFT

    42.46 GB

    VRAM

    —

    MTP

    314.6 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=56 running model_id=63 at IQ3_XS