Back to search results

Llama-3-8B-Instruct · Q8_0

Start a discussion
NVIDIA RTX 309024GBllama.cpp b4200L0 Self-reported

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q8_0) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

84.9 tok/s

Decode

Decode speed

636.8 tok/s

Prefill

Prefill speed

0.16 s

TTFT

Time to first token

9.1 GB

VRAM

VRAM usage

L0 Self-reported

1

Measured runs

1

Independent sources

Other

Source platforms

2026-10-06

Last verified

Performance

  1. Ollama · Q5_K_S Decode 67.97 · Prefill 263.38 ·
  2. Strata · IQ3_S Decode 155.86 · Prefill 503.14 ·
  3. Strata · Q5_K_M Decode 101.92 · Prefill 340.28 ·
  4. Ollama · IQ3_S Decode 90.89 · Prefill 298.18 ·
  5. Ollama · Q4_K_M Decode 84.07 · Prefill 419.77 ·
  6. Strata · IQ4_XS Decode 126.45 · Prefill 522.82 ·
  7. Strata · Q3_K_M Decode 136.06 · Prefill 696.33 ·
  8. llama.cpp · Q8_0 (current)Decode 84.9 · Prefill 636.8 ·
  9. llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
  10. llama.cpp · Q4_K_M Decode 149 · Prefill 1117.5 ·

Core figures

Decode (avg)
84.9 tok/s
Prefill (avg)
636.8 tok/s
TTFT (avg)
0.16 s
VRAM (avg)
9.1 GB
MTP acceptance rate
—
TTFB
— GB
Power draw
— W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q8_0
Framework
llama.cpp
Version
b4200
Context length
4096 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
9.1 GB
OS
Linux
Driver
570.65
CUDA
12.6

Sources & evidence

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

  1. L0 Self-reportedOtherOriginal link Verified on 2026-10-06

    b4200 · Linux · CUDA 12.6 · 4096 ctx

    84.9 tok/s

    Decode

    636.8 tok/s

    Prefill

    0.16 s

    TTFT

    9.1 GB

    VRAM

    —

    MTP

    — W

    Power draw

    L0 理论估算(add-1000-records-batch3)