Arao AI
Back to search results

Qwen3-1.7B · Q4_K_S

Start a discussion
NVIDIA RTX 508016GBllama.cpp v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_S) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

194.19 tok/s

Decode

Decode speed

976.97 tok/s

Prefill

Prefill speed

0.51 s

TTFT

Time to first token

4.88 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 (current)Decode 194.19 · Prefill 976.97 ·
  2. llama.cpp · Q8_0 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)
194.19 tok/s
Prefill (avg)
976.97 tok/s
TTFT (avg)
0.51 s
VRAM (avg)
4.88 GB
MTP acceptance rate
—
TTFB
1.55 GB
Power draw
255.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.41
Context length
2048 tokens
Batch size
256
GPU layers
99
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)
4.88 GB
OS
macOS 15.0
Driver
565.57
CUDA
12.8
Power draw
255.3 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

    v0.41 · macOS 15.0 · CUDA 12.8 · 2048 ctx

    194.19 tok/s

    Decode

    976.97 tok/s

    Prefill

    0.51 s

    TTFT

    4.88 GB

    VRAM

    —

    MTP

    255.3 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=14 running model_id=55 at Q4_K_S