Arao AI
Back to search results

Llama-3-8B-Instruct · IQ2_XS

Start a discussion
NVIDIA RTX 4080 Super16GBStrata v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (IQ2_XS) on NVIDIA RTX 4080 Super with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

334.52 tok/s

Decode

Decode speed

1,091.81 tok/s

Prefill

Prefill speed

2.26 s

TTFT

Time to first token

10.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Ollama · IQ3_XS Decode 190.92 · Prefill 657.75 ·
  2. Strata · IQ2_XS (current)Decode 334.52 · Prefill 1091.81 ·
  3. vLLM · Q3_K_S Decode 189.4 · Prefill 632.63 ·
  4. Ollama · IQ1_S Decode 212.31 · Prefill 982.11 ·

Core figures

Decode (avg)
334.52 tok/s
Prefill (avg)
1,091.81 tok/s
TTFT (avg)
2.26 s
VRAM (avg)
10.16 GB
MTP acceptance rate
0.75
TTFB
2.68 GB
Power draw
265.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
IQ2_XS
Framework
Strata
Version
v0.44
Context length
8192 tokens
Batch size
512
GPU layers
15
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)
10.16 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.8
Power draw
265.6 W

Sources & evidence

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

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

    v0.44 · Windows 11 24H2 · CUDA 12.8 · 8192 ctx

    334.52 tok/s

    Decode

    1,091.81 tok/s

    Prefill

    2.26 s

    TTFT

    10.16 GB

    VRAM

    0.75

    MTP

    265.6 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=20 running model_id=69 at IQ2_XS