Arao AI
Back to search results

Qwen3.8-9B · Q2_K

Start a discussion
NVIDIA RTX 509032GBvLLM v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q2_K) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

312.49 tok/s

Decode

Decode speed

1,617.22 tok/s

Prefill

Prefill speed

2.01 s

TTFT

Time to first token

12.5 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 304.42 · Prefill 1543.97 ·
  2. llama.cpp · Q3_K_S Decode 289.63 · Prefill 1418.95 ·
  3. vLLM · Q2_K (current)Decode 312.49 · Prefill 1617.22 ·
  4. vLLM · Q8_0 Decode 156.33 · Prefill 685.96 ·
  5. Ollama · Q3_K_S Decode 237.4 · Prefill 1150.93 ·
  6. Strata · Q3_K_L Decode 349.94 · Prefill 1124.59 ·
  7. vLLM · Q3_K_S Decode 286.31 · Prefill 1535.26 ·
  8. Strata · IQ1_S Decode 313.75 · Prefill 1522.32 ·
  9. Ollama · IQ4_XS Decode 224.73 · Prefill 806.05 ·
  10. Ollama · Q5_K_S Decode 182.89 · Prefill 696.63 ·
  11. Strata · Q5_K_S Decode 276.86 · Prefill 910.66 ·

Core figures

Decode (avg)
312.49 tok/s
Prefill (avg)
1,617.22 tok/s
TTFT (avg)
2.01 s
VRAM (avg)
12.5 GB
MTP acceptance rate
—
TTFB
2.5 GB
Power draw
365.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q2_K
Framework
vLLM
Version
v0.21
Context length
32768 tokens
Batch size
16
GPU layers
999
Flash Attention
On

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)
12.5 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
12.4
Power draw
365.7 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.21 · Windows 11 24H2 · CUDA 12.4 · 32768 ctx

    312.49 tok/s

    Decode

    1,617.22 tok/s

    Prefill

    2.01 s

    TTFT

    12.5 GB

    VRAM

    —

    MTP

    365.7 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=13 running model_id=52 at Q2_K