Arao AI
Back to search results

gemma-4-31B-it · IQ2_M

Start a discussion
NVIDIA RTX 509032GBStrata v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ2_M) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

284.29 tok/s

Decode

Decode speed

1,098.95 tok/s

Prefill

Prefill speed

0.1 s

TTFT

Time to first token

30.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Strata · IQ2_M (current)Decode 284.29 · Prefill 1098.95 ·
  2. vLLM · IQ2_M Decode 219.67 · Prefill 1152.52 ·
  3. llama.cpp · IQ2_M Decode 159.29 · Prefill 615.31 ·
  4. Ollama · IQ1_S Decode 146.23 · Prefill 719.62 ·
  5. vLLM · IQ2_XS Decode 145.1 · Prefill 1088.3 ·
  6. vLLM · Q5_K_M Decode 66.2 · Prefill 496.5 ·
  7. vLLM · Q4_K_M Decode 81 · Prefill 607.5 ·
  8. llama.cpp · IQ2_XS Decode 133.1 · Prefill 998.3 ·
  9. llama.cpp · Q5_K_M Decode 60.8 · Prefill 456 ·
  10. llama.cpp · Q4_K_M Decode 74.3 · Prefill 557.3 ·

Core figures

Decode (avg)
284.29 tok/s
Prefill (avg)
1,098.95 tok/s
TTFT (avg)
0.1 s
VRAM (avg)
30.4 GB
MTP acceptance rate
0.66
TTFB
2.27 GB
Power draw
471.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ2_M
Framework
Strata
Version
v0.23
Context length
16384 tokens
Batch size
512
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 RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
30.4 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.8
Power draw
471.2 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

    v0.23 · Windows 11 24H2 · CUDA 12.8 · 16384 ctx

    284.29 tok/s

    Decode

    1,098.95 tok/s

    Prefill

    0.1 s

    TTFT

    30.4 GB

    VRAM

    0.66

    MTP

    471.2 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=13 running model_id=63 at IQ2_M