Arao AI
Back to search results

Qwen3-1.7B · Q8_0

Start a discussion
NVIDIA RTX 508016GBllama.cpp v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q8_0) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

121.42 tok/s

Decode

Decode speed

409.38 tok/s

Prefill

Prefill speed

1.9 s

TTFT

Time to first token

6.21 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q4_K_S Decode 194.19 · Prefill 976.97 ·
  2. llama.cpp · Q8_0 (current)Decode 121.42 · Prefill 409.38 ·
  3. Ollama · Q3_K_M Decode 198.41 · Prefill 879.72 ·
  4. Ollama · Q8_0 Decode 116.38 · Prefill 555.86 ·

Core figures

Decode (avg)
121.42 tok/s
Prefill (avg)
409.38 tok/s
TTFT (avg)
1.9 s
VRAM (avg)
6.21 GB
MTP acceptance rate
—
TTFB
0.97 GB
Power draw
290.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q8_0
Framework
llama.cpp
Version
v0.29
Context length
2048 tokens
Batch size
512
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 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
6.21 GB
OS
Windows 11 23H2
Driver
555.85
CUDA
12.8
Power draw
290.2 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

    v0.29 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx

    121.42 tok/s

    Decode

    409.38 tok/s

    Prefill

    1.9 s

    TTFT

    6.21 GB

    VRAM

    —

    MTP

    290.2 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=14 running model_id=55 at Q8_0