Arao AI
Back to search results

Qwen3.5-0.8B · Q4_K_S

Start a discussion
NVIDIA RTX 508016GBStrata v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_S) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

363.26 tok/s

Decode

Decode speed

1,495.67 tok/s

Prefill

Prefill speed

2.13 s

TTFT

Time to first token

3.41 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 338.41 · Prefill 1613.66 ·
  2. Strata · FP16 Decode 178.36 · Prefill 737.11 ·
  3. Strata · Q4_K_S (current)Decode 363.26 · Prefill 1495.67 ·

Core figures

Decode (avg)
363.26 tok/s
Prefill (avg)
1,495.67 tok/s
TTFT (avg)
2.13 s
VRAM (avg)
3.41 GB
MTP acceptance rate
0.46
TTFB
2.91 GB
Power draw
319.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q4_K_S
Framework
Strata
Version
v0.27
Context length
2048 tokens
Batch size
256
GPU layers
5
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
3.41 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
319.9 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.27 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx

    363.26 tok/s

    Decode

    1,495.67 tok/s

    Prefill

    2.13 s

    TTFT

    3.41 GB

    VRAM

    0.46

    MTP

    319.9 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=14 running model_id=51 at Q4_K_S