Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q3_K_L

Start a discussion
NVIDIA RTX 4080 Super16GBStrata v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q3_K_L) on NVIDIA RTX 4080 Super with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

358.87 tok/s

Decode

Decode speed

1,331.79 tok/s

Prefill

Prefill speed

2.27 s

TTFT

Time to first token

6.64 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_S Decode 334.5 · Prefill 1159.32 ·
  2. Strata · Q3_K_L (current)Decode 358.87 · Prefill 1331.79 ·

Core figures

Decode (avg)
358.87 tok/s
Prefill (avg)
1,331.79 tok/s
TTFT (avg)
2.27 s
VRAM (avg)
6.64 GB
MTP acceptance rate
0.61
TTFB
2.87 GB
Power draw
298.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q3_K_L
Framework
Strata
Version
v0.42
Context length
4096 tokens
Batch size
1024
GPU layers
5
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 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
6.64 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.4
Power draw
298.6 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

    v0.42 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    358.87 tok/s

    Decode

    1,331.79 tok/s

    Prefill

    2.27 s

    TTFT

    6.64 GB

    VRAM

    0.61

    MTP

    298.6 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=20 running model_id=70 at Q3_K_L