Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
NVIDIA RTX 408016GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on NVIDIA RTX 4080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

141.07 tok/s

Decode

Decode speed

456.51 tok/s

Prefill

Prefill speed

1.39 s

TTFT

Time to first token

9.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · IQ3_S Decode 137.8 · Prefill 706.29 ·
  2. Ollama · IQ3_XS Decode 158.58 · Prefill 727 ·
  3. Strata · IQ3_S Decode 234.8 · Prefill 1203.48 ·
  4. Strata · IQ4_XS Decode 189.04 · Prefill 930.37 ·
  5. llama.cpp · IQ1_S (current)Decode 141.07 · Prefill 456.51 ·
  6. llama.cpp · IQ3_S Decode 105.08 · Prefill 472.34 ·
  7. vLLM · IQ1_S Decode 150.38 · Prefill 727.2 ·

Core figures

Decode (avg)
141.07 tok/s
Prefill (avg)
456.51 tok/s
TTFT (avg)
1.39 s
VRAM (avg)
9.16 GB
MTP acceptance rate
—
TTFB
1.13 GB
Power draw
349.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.46
Context length
16384 tokens
Batch size
512
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 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
9.16 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.4
Power draw
349.3 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.46 · Ubuntu 24.04 · CUDA 12.4 · 16384 ctx

    141.07 tok/s

    Decode

    456.51 tok/s

    Prefill

    1.39 s

    TTFT

    9.16 GB

    VRAM

    —

    MTP

    349.3 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=41 running model_id=53 at IQ1_S