Back to search results
Llama-3-8B-Instruct · Q4_K_S
NVIDIA RTX 409024GBllama.cpp v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q4_K_S) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
134.4 tok/s
Decode
Decode speed
594.59 tok/s
Prefill
Prefill speed
1.77 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
Today
Last verified
Performance
- llama.cpp · Q4_K_M Decode 146.97 · Prefill 902.58 ·
- llama.cpp · Q4_K_S (current)Decode 134.4 · Prefill 594.59 ·
- Strata · Q2_K Decode 254.93 · Prefill 1284 ·
- llama.cpp · Q8_0 Decode 91.4 · Prefill 685.5 ·
- llama.cpp · Q5_K_M Decode 133.3 · Prefill 999.8 ·
Core figures
- Decode (avg)
- 134.4 tok/s
- Prefill (avg)
- 594.59 tok/s
- TTFT (avg)
- 1.77 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.08 GB
- Power draw
- 355.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3-8B-Instruct
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.27
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 20
- 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)
- 15.2 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 355.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx
134.4 tok/s
Decode
594.59 tok/s
Prefill
1.77 s
TTFT
15.2 GB
VRAM
—
MTP
355.5 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=1 running model_id=69 at Q4_K_S