Arao AI
Back to search results

Qwen3-8B · IQ2_M

Start a discussion
NVIDIA RTX 508016GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

240.94 tok/s

Decode

Decode speed

1,234.91 tok/s

Prefill

Prefill speed

0.25 s

TTFT

Time to first token

10.84 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_S Decode 206.58 · Prefill 831.19 ·
  2. vLLM · IQ2_M (current)Decode 240.94 · Prefill 1234.91 ·
  3. Ollama · Q5_K_S Decode 128.2 · Prefill 585.03 ·
  4. Strata · IQ1_S Decode 376.58 · Prefill 1681.2 ·
  5. llama.cpp · Q5_K_S Decode 91.75 · Prefill 454.66 ·
  6. Ollama · Q3_K_L Decode 101.88 · Prefill 405.42 ·
  7. Strata · IQ4_XS Decode 144.31 · Prefill 545.08 ·

Core figures

Decode (avg)
240.94 tok/s
Prefill (avg)
1,234.91 tok/s
TTFT (avg)
0.25 s
VRAM (avg)
10.84 GB
MTP acceptance rate
—
TTFB
1.93 GB
Power draw
273.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ2_M
Framework
vLLM
Version
v0.27
Context length
32768 tokens
Batch size
32
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 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
10.84 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
273.9 W

Sources & evidence

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

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

    v0.27 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx

    240.94 tok/s

    Decode

    1,234.91 tok/s

    Prefill

    0.25 s

    TTFT

    10.84 GB

    VRAM

    —

    MTP

    273.9 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=14 running model_id=53 at IQ2_M