Arao AI
Back to search results

Qwen3.5-4B · Q2_K

Start a discussion
Intel Arc B58012GBvLLM v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q2_K) on Intel Arc B580 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

89.29 tok/s

Decode

Decode speed

348.31 tok/s

Prefill

Prefill speed

2.11 s

TTFT

Time to first token

6.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 98.24 · Prefill 506.66 ·
  2. llama.cpp · Q3_K_L Decode 70.52 · Prefill 317.93 ·
  3. vLLM · Q2_K (current)Decode 89.29 · Prefill 348.31 ·
  4. Strata · IQ3_S Decode 101.32 · Prefill 490.59 ·

Core figures

Decode (avg)
89.29 tok/s
Prefill (avg)
348.31 tok/s
TTFT (avg)
2.11 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
0.71 GB
Power draw
246.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q2_K
Framework
vLLM
Version
v0.35
Context length
4096 tokens
Batch size
8
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
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
246.2 W

Sources & evidence

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

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

    v0.35 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    89.29 tok/s

    Decode

    348.31 tok/s

    Prefill

    2.11 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    246.2 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=94 running model_id=48 at Q2_K