Arao AI
Back to search results

Qwen3.5-0.8B · FP16

Start a discussion
NVIDIA RTX 409024GBvLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (FP16) on NVIDIA RTX 4090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

161.03 tok/s

Decode

Decode speed

685.23 tok/s

Prefill

Prefill speed

0.92 s

TTFT

Time to first token

5.21 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 373.87 · Prefill 1737.06 ·
  2. llama.cpp · Q3_K_S Decode 364.6 · Prefill 1679.71 ·
  3. vLLM · FP16 (current)Decode 161.03 · Prefill 685.23 ·
  4. vLLM · IQ1_S Decode 328.9 · Prefill 1532.17 ·
  5. llama.cpp · IQ2_XS Decode 280.41 · Prefill 1104.34 ·
  6. llama.cpp · Q4_K_M Decode 278.24 · Prefill 916.88 ·
  7. vLLM · IQ3_XS Decode 302.65 · Prefill 1148.6 ·

Core figures

Decode (avg)
161.03 tok/s
Prefill (avg)
685.23 tok/s
TTFT (avg)
0.92 s
VRAM (avg)
5.21 GB
MTP acceptance rate
—
TTFB
1.29 GB
Power draw
378.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
FP16
Framework
vLLM
Version
v0.22
Context length
32768 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 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
5.21 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
378.1 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

    v0.22 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    161.03 tok/s

    Decode

    685.23 tok/s

    Prefill

    0.92 s

    TTFT

    5.21 GB

    VRAM

    —

    MTP

    378.1 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=1 running model_id=51 at FP16