Arao AI
Back to search results

Qwen3.5-0.8B · Q6_K

Start a discussion
NVIDIA RTX 408016GBvLLM v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q6_K) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

169.83 tok/s

Decode

Decode speed

688.66 tok/s

Prefill

Prefill speed

0.95 s

TTFT

Time to first token

3.78 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 · Q3_K_S 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 (current)Decode 169.83 · Prefill 688.66 ·
  6. Strata · Q3_K_S Decode 370.12 · Prefill 1878.16 ·

Core figures

Decode (avg)
169.83 tok/s
Prefill (avg)
688.66 tok/s
TTFT (avg)
0.95 s
VRAM (avg)
3.78 GB
MTP acceptance rate
—
TTFB
1.36 GB
Power draw
356.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q6_K
Framework
vLLM
Version
v0.43
Context length
16384 tokens
Batch size
8
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
Nominal VRAM
16 GB
Measured VRAM (avg)
3.78 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.6
Power draw
356.2 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

    v0.43 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    169.83 tok/s

    Decode

    688.66 tok/s

    Prefill

    0.95 s

    TTFT

    3.78 GB

    VRAM

    —

    MTP

    356.2 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=41 running model_id=51 at Q6_K