Back to search results

Llama-3.1-8B-Instruct · Q5_K_M

Start a discussion
NVIDIA RTX 409024GBllama.cpp v0.49L2 Cross-framework verified

This page aggregates 2 real-world runs of Llama-3.1-8B-Instruct (Q5_K_M) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

128.55 tok/s

Decode

Decode speed

827.45 tok/s

Prefill

Prefill speed

0.96 s

TTFT

Time to first token

12.06 GB

VRAM

VRAM usage

L2 Cross-framework verified

2

Measured runs

1

Independent sources

Other

Source platforms

2026-10-18

Last verified

Performance

  1. vLLM · IQ2_XS Decode 205.12 · Prefill 1126.08 ·
  2. Strata · Q4_K_M Decode 191.74 · Prefill 642.2 ·
  3. Strata · Q6_K Decode 151.86 · Prefill 574.29 ·
  4. llama.cpp · Q5_K_M (current)Decode 128.55 · Prefill 827.45 ·
  5. vLLM · Q4_K_M Decode 142.74 · Prefill 510.45 ·
  6. llama.cpp · Q8_0 Decode 91.4 · Prefill 685.5 ·
  7. llama.cpp · Q4_K_M Decode 160.5 · Prefill 1203.8 ·

Core figures

Decode (avg)
128.55 tok/s
Prefill (avg)
827.45 tok/s
TTFT (avg)
0.96 s
VRAM (avg)
12.06 GB
MTP acceptance rate
—
TTFB
0.99 GB
Power draw
331.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q5_K_M
Framework
llama.cpp
Version
v0.49
Context length
32768 tokens
Batch size
256
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 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
12.06 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
13.0
Power draw
331.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.49 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx

    123.8 tok/s

    Decode

    655.09 tok/s

    Prefill

    1.82 s

    TTFT

    17.72 GB

    VRAM

    —

    MTP

    331.6 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=1 running model_id=68 at Q5_K_M
  2. L0 Self-reportedOtherOriginal link Verified on 2026-10-06

    b4200 · Linux · CUDA 12.6 · 4096 ctx

    133.3 tok/s

    Decode

    999.8 tok/s

    Prefill

    0.1 s

    TTFT

    6.4 GB

    VRAM

    —

    MTP

    — W

    Power draw

    L0 理论估算(add-1000-records-batch3)