Arao AI
Back to search results

Qwen3.5-0.8B · Q6_K

Start a discussion
NVIDIA RTX 5070 Ti16GBvLLM v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q6_K) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

174.9 tok/s

Decode

Decode speed

685.31 tok/s

Prefill

Prefill speed

1.54 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

Today

Last verified

Performance

  1. vLLM · FP16 Decode 121.99 · Prefill 561.36 ·
  2. vLLM · Q6_K (current)Decode 174.9 · Prefill 685.31 ·
  3. Strata · Q5_K_M Decode 251.18 · Prefill 1222.13 ·
  4. Strata · Q6_K Decode 237.15 · Prefill 1031.12 ·

Core figures

Decode (avg)
174.9 tok/s
Prefill (avg)
685.31 tok/s
TTFT (avg)
1.54 s
VRAM (avg)
3.78 GB
MTP acceptance rate
—
TTFB
1.4 GB
Power draw
268.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q6_K
Framework
vLLM
Version
v0.44
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 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
3.78 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.8
Power draw
268.9 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

    v0.44 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    174.9 tok/s

    Decode

    685.31 tok/s

    Prefill

    1.54 s

    TTFT

    3.78 GB

    VRAM

    —

    MTP

    268.9 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=51 at Q6_K