LLaMA V2 7B

Q4_0 running on Apple M1 with macOS 26.5.2 Tahoe

PERFORMANCE / TOKENS PER SECONDApple Silicon

Prompt processing128.09tok/s

#94 in index

Token generation12.75tok/s

#94 in index

Run fingerprint

Enough context to make the number useful.

ModelLLaMA V2 7BDense architecture

QuantizationQ4_0Exact submitted variant

GPUApple M111.84 GB VRAM

GPU architectureApple SiliconMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · standard-auto · 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.