Mistral 7B

IQ3_M running on AMD Radeon VII with macOS 15.8.1 Sequoia

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing555.59tok/s

#147 in index

Token generation46.66tok/s

#148 in index

Run fingerprint

Enough context to make the number useful.

ModelMistral 7BDense architecture

QuantizationIQ3_MExact submitted variant

GPUAMD Radeon VII15.98 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.26App version used to capture and sign this run

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 result remains explicitly labeled as a community submission.