Arao AI
Back to search results

gemma-4-12B-it · Q5_K_S

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_S) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

64.98 tok/s

Decode

Decode speed

291.13 tok/s

Prefill

Prefill speed

1.68 s

TTFT

Time to first token

22.8 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 (current)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 Decode 129.13 · Prefill 417.63 ·

Core figures

Decode (avg)
64.98 tok/s
Prefill (avg)
291.13 tok/s
TTFT (avg)
1.68 s
VRAM (avg)
22.8 GB
MTP acceptance rate
—
TTFB
0.52 GB
Power draw
473.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q5_K_S
Framework
vLLM
Version
v0.29
Context length
4096 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

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)
22.8 GB
OS
macOS 15.0
Driver
565.57
CUDA
12.4
Power draw
473.2 W

Sources & evidence

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

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

    v0.29 · macOS 15.0 · CUDA 12.4 · 4096 ctx

    64.98 tok/s

    Decode

    291.13 tok/s

    Prefill

    1.68 s

    TTFT

    22.8 GB

    VRAM

    —

    MTP

    473.2 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=11 running model_id=65 at Q5_K_S