Arao AI
Back to search results

Qwen3-8B · IQ2_M

Start a discussion
Intel Arc B58012GBStrata v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on Intel Arc B580 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

88.38 tok/s

Decode

Decode speed

340.69 tok/s

Prefill

Prefill speed

0.76 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

Today

Last verified

Performance

  1. vLLM · Q3_K_M Decode 56.47 · Prefill 307.9 ·
  2. Strata · IQ2_M (current)Decode 88.38 · Prefill 340.69 ·
  3. Strata · Q3_K_M Decode 71.01 · Prefill 283.66 ·
  4. llama.cpp · Q3_K_M Decode 57.89 · Prefill 216.32 ·
  5. vLLM · IQ1_S Decode 82.24 · Prefill 450.81 ·
  6. vLLM · IQ2_XS Decode 78.59 · Prefill 324.5 ·

Core figures

Decode (avg)
88.38 tok/s
Prefill (avg)
340.69 tok/s
TTFT (avg)
0.76 s
VRAM (avg)
10.84 GB
MTP acceptance rate
0.54
TTFB
0.71 GB
Power draw
152.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ2_M
Framework
Strata
Version
v0.37
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
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
10.84 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.6
Power draw
152.4 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

    v0.37 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx

    88.38 tok/s

    Decode

    340.69 tok/s

    Prefill

    0.76 s

    TTFT

    10.84 GB

    VRAM

    0.54

    MTP

    152.4 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=94 running model_id=53 at IQ2_M