gpu4.pics
data via LocalScore
AMD EPYC 7352 24-Core Processor (znver2)
llamafile 0.9.1
126 GB VRAM AMD
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
14.3
tokens / sec
88 · Modest
Generation
14.3tok/s
higher is better
Prompt / prefill
266tok/s
higher is better
Time to first token
5.58 s
lower is better
Composite score
88
Model size
1.5B
Runtime
llamafile
AMD EPYC 7352 24-Core Processor (znver2) · 126 GB RAM · Linux · llamafile
gpu4.pics/r/ls-result-5

All benchmarks on this rig

ModelQuantGenPromptTTFTPowerPerf/W$/MtokScore
Llama 3.2 1B Instruct1.5BQ4_K_M14.32665.58 s88

How it stacks up — Llama 3.2 1B Instruct

AMD EPYC 7352 24-Core Processor (znver2)
14.3
NVIDIA L40S
355
NVIDIA RTX 3090 Ti
354
NVIDIA H100
335
NVIDIA RTX 3090
330
NVIDIA RTX A6000
315
NVIDIA A100 80GB
308