Community performance summary

Llama 3.2 1B

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

13 signed runs · 1 verified · 5 testers

Median prompt5655.79tok/s · 1388.43 to 8153.51

Median generation233.02tok/s · 85.26 to 297.01

Configurations3Q4_K_M · Q8_0 · UD-Q5_K_XL

Last observedSep 9RDNA 1 · RDNA 2 · RDNA 2 + GCN / Vega

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 tested6 groups

AMD Radeon RX 6900 XT ×24 runs→AMD Radeon Pro 5500M3 runs→AMD Radeon RX 6900 XT2 runs→AMD Radeon RX 6900 XT + AMD Radeon Vega1 run→AMD Radeon PRO W6800X2 runs→RX 6700 XT1 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 13 configurations

Verified benchmark Community submission

Model / quant	Hardware	Architecture	Prompt	Generation	Source
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT15.98 GB VRAM	RDNA 2	8088.69tok/s	297.01tok/s	Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon PRO W6800X31.98 GB VRAM	RDNA 2	5655.79tok/s	288.64tok/s	BirdsLikeWiresJul 22, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT ×231.97 GB VRAM	RDNA 2	5476.18tok/s	268.45tok/s	Dolphins1972Jul 18, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT ×231.97 GB VRAM	RDNA 2	8153.51tok/s	266.14tok/s	Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT ×231.97 GB VRAM	RDNA 2	8077.28tok/s	265.52tok/s	Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · comparison	RX 6700 XT12 GB VRAM	RDNA 2	2994tok/s	250tok/s	ToshLLM LabJul 15, 2026
Llama 3.2 1BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon PRO W6800X31.98 GB VRAM	RDNA 2	5805.79tok/s	233.02tok/s	BirdsLikeWiresJul 22, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT ×231.97 GB VRAM	RDNA 2	6491.86tok/s	207.43tok/s	ToshLLM communitySep 9, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT15.98 GB VRAM	RDNA 2	6224.67tok/s	206.18tok/s	ToshLLM communityAug 10, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon RX 6900 XT + AMD Radeon Vega31.97 GB VRAM	RDNA 2 + GCN / Vega	3047.25tok/s	113.04tok/s	ToshLLM communityAug 10, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon Pro 5500M7.98 GB VRAM	RDNA 1	1473.96tok/s	112.92tok/s	mnerdSep 7, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon Pro 5500M7.98 GB VRAM	RDNA 1	1602.61tok/s	103.89tok/s	mnerdAug 31, 2026
Llama 3.2 1BUD-Q5_K_XL · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon Pro 5500M7.98 GB VRAM	RDNA 1	1388.43tok/s	85.26tok/s	mnerdJul 31, 2026

Llama 3.2 1B

One clear view.Every recorded run.

Inspect every run.

No matching runs

One clear view.
Every recorded run.