Back to search results
Llama-3-8B-Instruct · Q5_K_S
NVIDIA RTX 408016GBvLLM v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
132.58 tok/s
Decode
Decode speed
716.19 tok/s
Prefill
Prefill speed
2.4 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
- vLLM · IQ3_XS Decode 205.69 · Prefill 981.9 ·
- vLLM · Q5_K_S (current)Decode 132.58 · Prefill 716.19 ·
- Strata · Q3_K_M Decode 260.87 · Prefill 961.11 ·
Core figures
- Decode (avg)
- 132.58 tok/s
- Prefill (avg)
- 716.19 tok/s
- TTFT (avg)
- 2.4 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.06 GB
- Power draw
- 301 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3-8B-Instruct
- Quantization
- Q5_K_S
- Framework
- vLLM
- Version
- v0.51
- Context length
- 32768 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 24H2
- Driver
- 560.94
- CUDA
- 13.0
- Power draw
- 301 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Windows 11 24H2 · CUDA 13.0 · 32768 ctx
132.58 tok/s
Decode
716.19 tok/s
Prefill
2.4 s
TTFT
15.2 GB
VRAM
—
MTP
301 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=41 running model_id=69 at Q5_K_S