GPT OSS 20B

Q4_K_M running on AMD Radeon RX 6700 XT

PERFORMANCE / TOKENS PER SECONDRDNA 2

Prompt processing1037.06tok/s

#9 in index

Token generation92.94tok/s

#8 in index

Run fingerprint

Enough context to make the number useful.

ModelGPT OSS 20BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon RX 6700 XT11.98 GB VRAM

GPU architectureRDNA 2Metal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · amd-gpu · Metal

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.