Back to search results
Llama-3.2-3B-Instruct · IQ3_S
NVIDIA RTX 4080 Super16GBvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ3_S) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
334.5 tok/s
Decode
Decode speed
1,159.32 tok/s
Prefill
Prefill speed
0.71 s
TTFT
Time to first token
6.26 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ3_S (current)Decode 334.5 · Prefill 1159.32 ·
- Strata · Q3_K_L Decode 358.87 · Prefill 1331.79 ·
Core figures
- Decode (avg)
- 334.5 tok/s
- Prefill (avg)
- 1,159.32 tok/s
- TTFT (avg)
- 0.71 s
- VRAM (avg)
- 6.26 GB
- MTP acceptance rate
- —
- TTFB
- 2.68 GB
- Power draw
- 317.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- IQ3_S
- Framework
- vLLM
- Version
- v0.50
- Context length
- 4096 tokens
- Batch size
- 8
- 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 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.26 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 317.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
334.5 tok/s
Decode
1,159.32 tok/s
Prefill
0.71 s
TTFT
6.26 GB
VRAM
—
MTP
317.8 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=70 at IQ3_S