Arao AI
Back to search results

Qwen3.5-0.8B · Q3_K_S

Start a discussion
NVIDIA RTX 408016GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_S) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

378.63 tok/s

Decode

Decode speed

1,756.55 tok/s

Prefill

Prefill speed

1.14 s

TTFT

Time to first token

3.19 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q3_K_S (current)Decode 378.63 · Prefill 1756.55 ·
  2. vLLM · Q5_K_M Decode 304.13 · Prefill 1485.96 ·
  3. Strata · IQ1_S Decode 334.33 · Prefill 1448.23 ·
  4. Strata · Q8_0 Decode 328.32 · Prefill 1297.3 ·
  5. vLLM · Q6_K Decode 169.83 · Prefill 688.66 ·
  6. Strata · Q3_K_S Decode 370.12 · Prefill 1878.16 ·

Core figures

Decode (avg)
378.63 tok/s
Prefill (avg)
1,756.55 tok/s
TTFT (avg)
1.14 s
VRAM (avg)
3.19 GB
MTP acceptance rate
—
TTFB
3.03 GB
Power draw
288.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q3_K_S
Framework
vLLM
Version
v0.29
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 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
3.19 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.4
Power draw
288.9 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

    v0.29 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    378.63 tok/s

    Decode

    1,756.55 tok/s

    Prefill

    1.14 s

    TTFT

    3.19 GB

    VRAM

    —

    MTP

    288.9 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=41 running model_id=51 at Q3_K_S