Arao AI
Back to search results

gemma-4-12B-it · IQ3_XS

Start a discussion
AMD Radeon RX 7900 XTX24GBStrata v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ3_XS) on AMD Radeon RX 7900 XTX with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

129.13 tok/s

Decode

Decode speed

417.63 tok/s

Prefill

Prefill speed

1.71 s

TTFT

Time to first token

17.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q4_K_S Decode 86.73 · Prefill 462.81 ·
  2. vLLM · Q5_K_S Decode 64.98 · Prefill 291.13 ·
  3. Ollama · IQ2_M Decode 92.49 · Prefill 473.64 ·
  4. Ollama · Q4_K_S Decode 67.64 · Prefill 313.4 ·
  5. Strata · IQ3_XS (current)Decode 129.13 · Prefill 417.63 ·

Core figures

Decode (avg)
129.13 tok/s
Prefill (avg)
417.63 tok/s
TTFT (avg)
1.71 s
VRAM (avg)
17.72 GB
MTP acceptance rate
0.67
TTFB
1.03 GB
Power draw
370.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ3_XS
Framework
Strata
Version
v0.23
Context length
2048 tokens
Batch size
256
GPU layers
12
Flash Attention
On

Hardware

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

GPU
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
17.72 GB
OS
macOS 15.0
Driver
555.85
CUDA
12.8
Power draw
370.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.23 · macOS 15.0 · CUDA 12.8 · 2048 ctx

    129.13 tok/s

    Decode

    417.63 tok/s

    Prefill

    1.71 s

    TTFT

    17.72 GB

    VRAM

    0.67

    MTP

    370.8 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=11 running model_id=65 at IQ3_XS