Arao AI
Back to search results

Qwen3.8-9B · Q5_K_S

Start a discussion
NVIDIA RTX 509032GBStrata v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

276.86 tok/s

Decode

Decode speed

910.66 tok/s

Prefill

Prefill speed

1.16 s

TTFT

Time to first token

19.11 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ4_XS Decode 224.73 · Prefill 806.05 ·
  2. Ollama · Q5_K_S Decode 182.89 · Prefill 696.63 ·
  3. Strata · IQ1_S Decode 329.29 · Prefill 1427.88 ·
  4. Strata · Q5_K_S (current)Decode 276.86 · Prefill 910.66 ·

Core figures

Decode (avg)
276.86 tok/s
Prefill (avg)
910.66 tok/s
TTFT (avg)
1.16 s
VRAM (avg)
19.11 GB
MTP acceptance rate
0.54
TTFB
2.21 GB
Power draw
480.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q5_K_S
Framework
Strata
Version
v0.54
Context length
8192 tokens
Batch size
256
GPU layers
15
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)
19.11 GB
OS
macOS 15.0
Driver
555.85
CUDA
12.6
Power draw
480.9 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

    v0.54 · macOS 15.0 · CUDA 12.6 · 8192 ctx

    276.86 tok/s

    Decode

    910.66 tok/s

    Prefill

    1.16 s

    TTFT

    19.11 GB

    VRAM

    0.54

    MTP

    480.9 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=13 running model_id=52 at Q5_K_S