Arao AI
Back to search results

Qwen3.8-9B · Q4_K_M

Start a discussion
NVIDIA RTX 508016GBvLLM v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

152.58 tok/s

Decode

Decode speed

685.84 tok/s

Prefill

Prefill speed

2.25 s

TTFT

Time to first token

15.2 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_M (current)Decode 152.58 · Prefill 685.84 ·
  2. Strata · IQ2_M Decode 294.71 · Prefill 1507.15 ·
  3. Strata · IQ3_XS Decode 265.22 · Prefill 1010.61 ·
  4. llama.cpp · IQ4_XS Decode 97.14 · Prefill 496.38 ·
  5. llama.cpp · Q3_K_M Decode 108.92 · Prefill 455.22 ·
  6. vLLM · IQ2_M Decode 131.31 · Prefill 559.09 ·

Core figures

Decode (avg)
152.58 tok/s
Prefill (avg)
685.84 tok/s
TTFT (avg)
2.25 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.22 GB
Power draw
237.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_M
Framework
vLLM
Version
v0.33
Context length
2048 tokens
Batch size
8
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
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
13.0
Power draw
237.7 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

    v0.33 · Windows 11 23H2 · CUDA 13.0 · 2048 ctx

    152.58 tok/s

    Decode

    685.84 tok/s

    Prefill

    2.25 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    237.7 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=14 running model_id=52 at Q4_K_M