Arao AI
Back to search results

Qwen3.5-4B · Q5_K_M

Start a discussion
NVIDIA RTX 4080 Super16GBvLLM v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_M) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

152.06 tok/s

Decode

Decode speed

772.68 tok/s

Prefill

Prefill speed

0.83 s

TTFT

Time to first token

9.91 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q5_K_M (current)Decode 152.06 · Prefill 772.68 ·
  2. Ollama · Q3_K_L Decode 202.33 · Prefill 955.67 ·

Core figures

Decode (avg)
152.06 tok/s
Prefill (avg)
772.68 tok/s
TTFT (avg)
0.83 s
VRAM (avg)
9.91 GB
MTP acceptance rate
—
TTFB
1.22 GB
Power draw
237.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.33
Context length
2048 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

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)
9.91 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
237.4 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

    v0.33 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    152.06 tok/s

    Decode

    772.68 tok/s

    Prefill

    0.83 s

    TTFT

    9.91 GB

    VRAM

    —

    MTP

    237.4 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=48 at Q5_K_M