DeepSeek Coder V2 Lite Instruct

IQ2_XS running on AMD Radeon Pro 560X with macOS 15.8 Sequoia

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing111.55tok/s

#311 in index

Token generation13.52tok/s

#284 in index

Run fingerprint

Enough context to make the number useful.

ModelDeepSeek Coder V2 Lite InstructMoE architecture

QuantizationIQ2_XSExact submitted variant

GPUAMD Radeon Pro 560X4 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 16 · amd-gpu · Metal

ToshLLM versionv0.87.9App 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.