Arao AI
Back to search results

Qwen3-8B · IQ2_M

Start a discussion
Qualcomm Snapdragon X EliteStrata v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on Qualcomm Snapdragon X Elite with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

86.12 tok/s

Decode

Decode speed

422.03 tok/s

Prefill

Prefill speed

0.48 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

2 days ago

Last verified

Performance

  1. vLLM · Q2_K Decode 69.03 · Prefill 343.27 ·
  2. vLLM · Q3_K_S Decode 55.63 · Prefill 229.65 ·
  3. Strata · IQ2_M (current)Decode 86.12 · Prefill 422.03 ·
  4. Strata · Q3_K_M Decode 73.79 · Prefill 405.35 ·

Core figures

Decode (avg)
86.12 tok/s
Prefill (avg)
422.03 tok/s
TTFT (avg)
0.48 s
VRAM (avg)
10.84 GB
MTP acceptance rate
0.74
TTFB
0.69 GB
Power draw
23 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ2_M
Framework
Strata
Version
v0.53
Context length
16384 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
Qualcomm Snapdragon X Elite
Measured VRAM (avg)
10.84 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
23 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.53 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    86.12 tok/s

    Decode

    422.03 tok/s

    Prefill

    0.48 s

    TTFT

    10.84 GB

    VRAM

    0.74

    MTP

    23 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=104 running model_id=53 at IQ2_M