Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ2_M

Start a discussion
NVIDIA RTX 4080 Super16GBvLLM v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_M) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

224.52 tok/s

Decode

Decode speed

1,147.46 tok/s

Prefill

Prefill speed

0.45 s

TTFT

Time to first token

10.84 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_M (current)Decode 224.52 · Prefill 1147.46 ·
  2. vLLM · Q3_K_L Decode 177.01 · Prefill 908.47 ·
  3. Ollama · IQ2_M Decode 204.79 · Prefill 1109.54 ·

Core figures

Decode (avg)
224.52 tok/s
Prefill (avg)
1,147.46 tok/s
TTFT (avg)
0.45 s
VRAM (avg)
10.84 GB
MTP acceptance rate
—
TTFB
1.8 GB
Power draw
290.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ2_M
Framework
vLLM
Version
v0.21
Context length
8192 tokens
Batch size
8
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 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
10.84 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.4
Power draw
290.5 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

    v0.21 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx

    224.52 tok/s

    Decode

    1,147.46 tok/s

    Prefill

    0.45 s

    TTFT

    10.84 GB

    VRAM

    —

    MTP

    290.5 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=68 at IQ2_M