Community performance summary

LLaMA V2 7B

3 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

3 signed runs · 1 verified · 3 testers

Median prompt655.45tok/s · 128.09 to 1508.5

Median generation72.73tok/s · 12.75 to 105.77

Configurations1Q4_0

Last observedAug 6Apple Silicon · RDNA · RDNA 2

What the results show

One clear view.
Every recorded run.

Measurements from comparable hardware and models are presented together. Medians show typical performance, while every signed run remains available below for inspection and sharing.

Hardware tested3 groups

AMD Radeon GFX10, 16 GB1 run→AMD Radeon RX 6700 XT1 run→Apple M11 run→

Recorded evidence

Inspect every run.

Open any result to review its exact hardware, model configuration, measurements and submission details.

AppSort

1 to 8 of 3 configurations

Verified benchmark Community submission

Model / quant	Hardware	Architecture	Prompt	Generation	Source
LLaMA V2 7BQ4_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon GFX10, 16 GB15.98 GB VRAM	RDNA	1508.5tok/s	105.77tok/s	ToshLLM communityAug 6, 2026
LLaMA V2 7BQ4_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6700 XT11.98 GB VRAM	RDNA 2	655.45tok/s	72.73tok/s	ToshLLM LabJul 20, 2026
LLaMA V2 7BQ4_0 · Dense · Signed ToshLLM app · standard-auto · Metal · comparison	Apple M111.84 GB VRAM	Apple Silicon	128.09tok/s	12.75tok/s	bastenJul 18, 2026

LLaMA V2 7B

One clear view.Every recorded run.

Inspect every run.

No matching runs

One clear view.
Every recorded run.