Qwen2.5 Coder 7B

Q4_K_M running on AMD Radeon Pro 580 with macOS 14.7.5 Sonoma

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing144.55tok/s

#115 in index

Token generation14.75tok/s

#106 in index

Run fingerprint

Enough context to make the number useful.

ModelQwen2.5 Coder 7BDense architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Pro 5808 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyDenseSigned 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 result remains explicitly labeled as a community submission.