Arao AI
Back to search results

Qwen3.5-0.8B · Q8_0

Start a discussion
NVIDIA RTX 509032GBOllama v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q8_0) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

384.44 tok/s

Decode

Decode speed

1,342.7 tok/s

Prefill

Prefill speed

1.18 s

TTFT

Time to first token

4.03 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · Q3_K_L Decode 320.91 · Prefill 1586.97 ·
  2. Ollama · Q8_0 (current)Decode 384.44 · Prefill 1342.7 ·
  3. Strata · FP16 Decode 337.54 · Prefill 1202.28 ·
  4. Strata · Q6_K Decode 317.49 · Prefill 1303.51 ·

Core figures

Decode (avg)
384.44 tok/s
Prefill (avg)
1,342.7 tok/s
TTFT (avg)
1.18 s
VRAM (avg)
4.03 GB
MTP acceptance rate
—
TTFB
3.08 GB
Power draw
516.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q8_0
Framework
Ollama
Version
v0.47
Context length
32768 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
4.03 GB
OS
macOS 15.0
Driver
570.86
CUDA
12.6
Power draw
516.1 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

    v0.47 · macOS 15.0 · CUDA 12.6 · 32768 ctx

    384.44 tok/s

    Decode

    1,342.7 tok/s

    Prefill

    1.18 s

    TTFT

    4.03 GB

    VRAM

    —

    MTP

    516.1 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=13 running model_id=51 at Q8_0