Arao AI
Back to search results

Qwen3.8-9B · IQ3_XS

Start a discussion
NVIDIA RTX 508016GBStrata v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_XS) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

265.22 tok/s

Decode

Decode speed

1,010.61 tok/s

Prefill

Prefill speed

0.79 s

TTFT

Time to first token

13.82 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 Decode 152.58 · Prefill 685.84 ·
  2. Strata · IQ2_M Decode 294.71 · Prefill 1507.15 ·
  3. Strata · IQ3_XS (current)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)
265.22 tok/s
Prefill (avg)
1,010.61 tok/s
TTFT (avg)
0.79 s
VRAM (avg)
13.82 GB
MTP acceptance rate
0.71
TTFB
2.12 GB
Power draw
260.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ3_XS
Framework
Strata
Version
v0.45
Context length
32768 tokens
Batch size
256
GPU layers
8
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)
13.82 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.4
Power draw
260.3 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

    v0.45 · Windows 11 24H2 · CUDA 12.4 · 32768 ctx

    265.22 tok/s

    Decode

    1,010.61 tok/s

    Prefill

    0.79 s

    TTFT

    13.82 GB

    VRAM

    0.71

    MTP

    260.3 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=52 at IQ3_XS