Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q5_K_M

Start a discussion
NVIDIA RTX 4080 Super16GBStrata v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q5_K_M) on NVIDIA RTX 4080 Super with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

179.72 tok/s

Decode

Decode speed

584.63 tok/s

Prefill

Prefill speed

2.5 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 201.4 · Prefill 1061.69 ·
  2. Strata · IQ2_XS Decode 307.75 · Prefill 1104.97 ·
  3. Strata · Q5_K_M (current)Decode 179.72 · Prefill 584.63 ·
  4. vLLM · IQ2_M Decode 224.52 · Prefill 1147.46 ·
  5. vLLM · Q3_K_L Decode 177.01 · Prefill 908.47 ·
  6. Ollama · IQ2_M Decode 204.79 · Prefill 1109.54 ·

Core figures

Decode (avg)
179.72 tok/s
Prefill (avg)
584.63 tok/s
TTFT (avg)
2.5 s
VRAM (avg)
15.2 GB
MTP acceptance rate
0.77
TTFB
1.44 GB
Power draw
226.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q5_K_M
Framework
Strata
Version
v0.39
Context length
4096 tokens
Batch size
512
GPU layers
5
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)
15.2 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
226.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.39 · Ubuntu 24.04 · CUDA 12.8 · 4096 ctx

    179.72 tok/s

    Decode

    584.63 tok/s

    Prefill

    2.5 s

    TTFT

    15.2 GB

    VRAM

    0.77

    MTP

    226.5 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=20 running model_id=68 at Q5_K_M