Arao AI
Back to search results

gemma-4-26B-A4B-it · Q4_K_M

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM 0.7.3L0 Self-reported

This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (Q4_K_M) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

48.2 tok/s

Decode

Decode speed

361.5 tok/s

Prefill

Prefill speed

0.28 s

TTFT

Time to first token

16 GB

VRAM

VRAM usage

L0 Self-reported

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_XS Decode 86.5 · Prefill 648.8 ·
  2. vLLM · Q5_K_M Decode 39.5 · Prefill 296.3 ·
  3. vLLM · Q4_K_M (current)Decode 48.2 · Prefill 361.5 ·
  4. llama.cpp · IQ2_XS Decode 79.4 · Prefill 595.5 ·
  5. llama.cpp · Q5_K_M Decode 36.2 · Prefill 271.5 ·
  6. llama.cpp · Q4_K_M Decode 44.2 · Prefill 331.5 ·

Core figures

Decode (avg)
48.2 tok/s
Prefill (avg)
361.5 tok/s
TTFT (avg)
0.28 s
VRAM (avg)
16 GB
MTP acceptance rate
—
TTFB
— GB
Power draw
— W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-26B-A4B-it
Quantization
Q4_K_M
Framework
vLLM
Version
0.7.3
Context length
4096 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
16 GB
OS
Linux
Driver
570.65
CUDA
12.6

Sources & evidence

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

  1. L0 Self-reportedOtherOriginal link Verified on 2026-10-06

    0.7.3 · Linux · CUDA 12.6 · 4096 ctx

    48.2 tok/s

    Decode

    361.5 tok/s

    Prefill

    0.28 s

    TTFT

    16 GB

    VRAM

    —

    MTP

    — W

    Power draw

    L0 理论估算（add-1000-records-batch3）