Arao AI
Back to search results

Llama-3-8B-Instruct · IQ3_XS

Start a discussion
NVIDIA RTX 408016GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ3_XS) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

205.69 tok/s

Decode

Decode speed

981.9 tok/s

Prefill

Prefill speed

0.76 s

TTFT

Time to first token

12.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_XS (current)Decode 205.69 · Prefill 981.9 ·
  2. vLLM · Q5_K_S Decode 132.58 · Prefill 716.19 ·
  3. Strata · Q3_K_M Decode 260.87 · Prefill 961.11 ·

Core figures

Decode (avg)
205.69 tok/s
Prefill (avg)
981.9 tok/s
TTFT (avg)
0.76 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
1.65 GB
Power draw
288.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ3_XS
Framework
vLLM
Version
v0.27
Context length
16384 tokens
Batch size
32
GPU layers
999
Flash Attention
On

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)
12.52 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
13.0
Power draw
288.7 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.27 · Windows 11 23H2 · CUDA 13.0 · 16384 ctx

    205.69 tok/s

    Decode

    981.9 tok/s

    Prefill

    0.76 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    288.7 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=41 running model_id=69 at IQ3_XS