Arao AI
Back to search results

Qwen3.5-0.8B · Q3_K_L

Start a discussion
NVIDIA RTX 509032GBOllama v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_L) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

320.91 tok/s

Decode

Decode speed

1,586.97 tok/s

Prefill

Prefill speed

0.89 s

TTFT

Time to first token

3.31 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 (current)Decode 320.91 · Prefill 1586.97 ·
  2. Ollama · Q8_0 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)
320.91 tok/s
Prefill (avg)
1,586.97 tok/s
TTFT (avg)
0.89 s
VRAM (avg)
3.31 GB
MTP acceptance rate
—
TTFB
2.57 GB
Power draw
599.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q3_K_L
Framework
Ollama
Version
v0.24
Context length
2048 tokens
Batch size
256
GPU layers
28
Flash Attention
Off

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)
3.31 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.8
Power draw
599.1 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

    v0.24 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    320.91 tok/s

    Decode

    1,586.97 tok/s

    Prefill

    0.89 s

    TTFT

    3.31 GB

    VRAM

    —

    MTP

    599.1 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=13 running model_id=51 at Q3_K_L