Arao AI
Back to search results

Qwen3.5-0.8B · IQ1_S

Start a discussion
NVIDIA RTX 4080 Super16GBvLLM v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ1_S) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

314.79 tok/s

Decode

Decode speed

1,409.84 tok/s

Prefill

Prefill speed

0.83 s

TTFT

Time to first token

2.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q4_K_M Decode 344.73 · Prefill 1737.55 ·
  2. vLLM · IQ1_S (current)Decode 314.79 · Prefill 1409.84 ·

Core figures

Decode (avg)
314.79 tok/s
Prefill (avg)
1,409.84 tok/s
TTFT (avg)
0.83 s
VRAM (avg)
2.8 GB
MTP acceptance rate
—
TTFB
2.52 GB
Power draw
262.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ1_S
Framework
vLLM
Version
v0.40
Context length
8192 tokens
Batch size
16
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 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
2.8 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
13.0
Power draw
262.7 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

    v0.40 · Windows 11 24H2 · CUDA 13.0 · 8192 ctx

    314.79 tok/s

    Decode

    1,409.84 tok/s

    Prefill

    0.83 s

    TTFT

    2.8 GB

    VRAM

    —

    MTP

    262.7 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=51 at IQ1_S