Arao AI
Back to search results

Qwen3.5-0.8B · FP16

Start a discussion
NVIDIA RTX 509032GBStrata v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (FP16) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

337.54 tok/s

Decode

Decode speed

1,202.28 tok/s

Prefill

Prefill speed

1.24 s

TTFT

Time to first token

5.21 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 Decode 384.44 · Prefill 1342.7 ·
  3. Strata · FP16 (current)Decode 337.54 · Prefill 1202.28 ·
  4. Strata · Q6_K Decode 317.49 · Prefill 1303.51 ·

Core figures

Decode (avg)
337.54 tok/s
Prefill (avg)
1,202.28 tok/s
TTFT (avg)
1.24 s
VRAM (avg)
5.21 GB
MTP acceptance rate
0.58
TTFB
2.7 GB
Power draw
511.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
FP16
Framework
Strata
Version
v0.42
Context length
8192 tokens
Batch size
256
GPU layers
8
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)
5.21 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.8
Power draw
511.3 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

    v0.42 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    337.54 tok/s

    Decode

    1,202.28 tok/s

    Prefill

    1.24 s

    TTFT

    5.21 GB

    VRAM

    0.58

    MTP

    511.3 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=13 running model_id=51 at FP16