gpu4.pics
data via LocalScore
NVIDIA RTX 4080
16 GB VRAM NVIDIA 320 W TDP
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
247
tokens / sec
3,780 · Excellent #9 of 768
Generation
247tok/s
higher is better
Prompt / prefill
17,479tok/s
higher is better
Time to first token
80 ms
lower is better
Composite score
3,780
Model size
1.5B
Runtime
gpu4.pics/r/ls-nvidia-rtx-4080-llama-32-1b-instruct-q4-k-m

All benchmarks on this rig

ModelQuantGenPromptTTFTPowerPerf/W$/MtokScore
Llama 3.2 1B Instruct1.5BQ4_K_M24717,47980 ms3,780

How it stacks up — Llama 3.2 1B Instruct

NVIDIA RTX 4080
247
NVIDIA L40S
355
NVIDIA RTX 3090 Ti
354
NVIDIA H100
335
NVIDIA RTX 3090
330
NVIDIA RTX A6000
315
NVIDIA A100 80GB
308