gpu4.pics
data via LocalScore
NVIDIA Tesla V100
32 GB VRAM NVIDIA 300 W TDP
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
248
tokens / sec
2,545 · Excellent #39 of 768
Generation
248tok/s
higher is better
Prompt / prefill
8,984tok/s
higher is better
Time to first token
135 ms
lower is better
Composite score
2,545
Model size
1.5B
Runtime
gpu4.pics/r/ls-nvidia-tesla-v100-llama-32-1b-instruct-q4-k-m

All benchmarks on this rig

ModelQuantGenPromptTTFTPowerPerf/W$/MtokScore
Llama 3.2 1B Instruct1.5BQ4_K_M2488,984135 ms2,545

How it stacks up — Llama 3.2 1B Instruct

NVIDIA Tesla V100
248
NVIDIA L40S
355
NVIDIA RTX 3090 Ti
354
NVIDIA H100
335
NVIDIA RTX 3090
330
NVIDIA RTX A6000
315
NVIDIA A100 80GB
308