Arao AI
Back to search results

Qwen3.8-9B · Q5_K_S

Start a discussion
NVIDIA RTX 309024GBOllama v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_S) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

58.86 tok/s

Decode

Decode speed

223.43 tok/s

Prefill

Prefill speed

0.54 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. llama.cpp · IQ2_XS Decode 98.31 · Prefill 360.63 ·
  2. llama.cpp · Q3_K_L Decode 79.17 · Prefill 416.87 ·
  3. Ollama · Q5_K_S (current)Decode 58.86 · Prefill 223.43 ·
  4. Ollama · Q8_0 Decode 46.15 · Prefill 154.63 ·
  5. llama.cpp · Q3_K_S Decode 130.89 · Prefill 575.17 ·
  6. Ollama · IQ4_XS Decode 98.13 · Prefill 496.33 ·

Core figures

Decode (avg)
58.86 tok/s
Prefill (avg)
223.43 tok/s
TTFT (avg)
0.54 s
VRAM (avg)
19.11 GB
MTP acceptance rate
—
TTFB
0.47 GB
Power draw
312.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.20
Context length
8192 tokens
Batch size
256
GPU layers
28
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
19.11 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
312.2 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.20 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    58.86 tok/s

    Decode

    223.43 tok/s

    Prefill

    0.54 s

    TTFT

    19.11 GB

    VRAM

    —

    MTP

    312.2 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=2 running model_id=52 at Q5_K_S