Arao AI
Back to search results

Llama-3-8B-Instruct · Q3_K_M

Start a discussion
NVIDIA RTX 408016GBStrata v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q3_K_M) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

260.87 tok/s

Decode

Decode speed

961.11 tok/s

Prefill

Prefill speed

1.49 s

TTFT

Time to first token

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

Core figures

Decode (avg)
260.87 tok/s
Prefill (avg)
961.11 tok/s
TTFT (avg)
1.49 s
VRAM (avg)
13.52 GB
MTP acceptance rate
0.77
TTFB
2.09 GB
Power draw
282 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q3_K_M
Framework
Strata
Version
v0.37
Context length
2048 tokens
Batch size
512
GPU layers
8
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)
13.52 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
13.0
Power draw
282 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

    v0.37 · Ubuntu 22.04 · CUDA 13.0 · 2048 ctx

    260.87 tok/s

    Decode

    961.11 tok/s

    Prefill

    1.49 s

    TTFT

    13.52 GB

    VRAM

    0.77

    MTP

    282 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=41 running model_id=69 at Q3_K_M