Arao AI
Back to search results

Llama-3-8B-Instruct · Q3_K_S

Start a discussion
NVIDIA RTX 3060 12GB12GBStrata v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q3_K_S) on NVIDIA RTX 3060 12GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

98.81 tok/s

Decode

Decode speed

492.63 tok/s

Prefill

Prefill speed

1 s

TTFT

Time to first token

11.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Strata · IQ1_S Decode 126.53 · Prefill 600.27 ·
  2. Strata · Q3_K_S (current)Decode 98.81 · Prefill 492.63 ·

Core figures

Decode (avg)
98.81 tok/s
Prefill (avg)
492.63 tok/s
TTFT (avg)
1 s
VRAM (avg)
11.4 GB
MTP acceptance rate
0.55
TTFB
0.79 GB
Power draw
148 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q3_K_S
Framework
Strata
Version
v0.39
Context length
4096 tokens
Batch size
512
GPU layers
8
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
11.4 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.6
Power draw
148 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

    v0.39 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx

    98.81 tok/s

    Decode

    492.63 tok/s

    Prefill

    1 s

    TTFT

    11.4 GB

    VRAM

    0.55

    MTP

    148 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=15 running model_id=69 at Q3_K_S