Back to search results
Llama-3.1-8B-Instruct · IQ1_S
NVIDIA RTX 4070 Ti12GBvLLM v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ1_S) on NVIDIA RTX 4070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
188.65 tok/s
Decode
Decode speed
681.35 tok/s
Prefill
Prefill speed
2.06 s
TTFT
Time to first token
9.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ1_S (current)Decode 188.65 · Prefill 681.35 ·
Core figures
- Decode (avg)
- 188.65 tok/s
- Prefill (avg)
- 681.35 tok/s
- TTFT (avg)
- 2.06 s
- VRAM (avg)
- 9.16 GB
- MTP acceptance rate
- —
- TTFB
- 1.51 GB
- Power draw
- 271.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.47
- Context length
- 4096 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4070 Ti
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 9.16 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 13.0
- Power draw
- 271.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Windows 11 23H2 · CUDA 13.0 · 4096 ctx
188.65 tok/s
Decode
681.35 tok/s
Prefill
2.06 s
TTFT
9.16 GB
VRAM
—
MTP
271.7 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=42 running model_id=68 at IQ1_S