Arao AI
Back to search results

Qwen3.5-0.8B · IQ4_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

206.77 tok/s

Decode

Decode speed

955.7 tok/s

Prefill

Prefill speed

2.22 s

TTFT

Time to first token

3.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · FP16 Decode 128.16 · Prefill 630.91 ·
  2. vLLM · Q4_K_S Decode 240.41 · Prefill 996.87 ·
  3. Ollama · Q5_K_S Decode 177.61 · Prefill 661.12 ·
  4. Ollama · Q6_K Decode 170.01 · Prefill 704.45 ·
  5. vLLM · IQ4_XS (current)Decode 206.77 · Prefill 955.7 ·
  6. vLLM · Q3_K_S Decode 239.77 · Prefill 1073.87 ·
  7. Ollama · IQ1_S Decode 259.18 · Prefill 1280.06 ·

Core figures

Decode (avg)
206.77 tok/s
Prefill (avg)
955.7 tok/s
TTFT (avg)
2.22 s
VRAM (avg)
3.34 GB
MTP acceptance rate
—
TTFB
1.65 GB
Power draw
359.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ4_XS
Framework
vLLM
Version
v0.45
Context length
32768 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
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
3.34 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.4
Power draw
359.3 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.45 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    206.77 tok/s

    Decode

    955.7 tok/s

    Prefill

    2.22 s

    TTFT

    3.34 GB

    VRAM

    —

    MTP

    359.3 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=3 running model_id=51 at IQ4_XS