Llama 3.2 1B

Q4_K_M running on RX 6700 XT

PERFORMANCE / TOKENS PER SECONDRDNA 2

Prompt processing2,994tok/s

#1 in index

Token generation250tok/s

#1 in index

Run fingerprint

Enough context to make the number useful.

ModelLlama 3.2 1BDense architecture

QuantizationQ4_K_MExact submitted variant

GPURX 6700 XT12 GB VRAM

GPU architectureRDNA 2Metal backend

Test context512prompt tokens

Model familyDenseStandard configuration

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This run was reproduced by ToshLLM Lab.