Back to search results
Llama-3-8B-Instruct · Q3_K_S
NVIDIA RTX 508016GBOllama v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q3_K_S) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
209.77 tok/s
Decode
Decode speed
751.17 tok/s
Prefill
Prefill speed
0.57 s
TTFT
Time to first token
13.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q5_K_M Decode 163.66 · Prefill 702.95 ·
- Ollama · Q3_K_S (current)Decode 209.77 · Prefill 751.17 ·
Core figures
- Decode (avg)
- 209.77 tok/s
- Prefill (avg)
- 751.17 tok/s
- TTFT (avg)
- 0.57 s
- VRAM (avg)
- 13.02 GB
- MTP acceptance rate
- —
- TTFB
- 1.68 GB
- Power draw
- 307.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3-8B-Instruct
- Quantization
- Q3_K_S
- Framework
- Ollama
- Version
- v0.53
- Context length
- 32768 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 13.02 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 307.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx
209.77 tok/s
Decode
751.17 tok/s
Prefill
0.57 s
TTFT
13.02 GB
VRAM
—
MTP
307.9 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=14 running model_id=69 at Q3_K_S