Google cloud models

59 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.

Model	Intelligence	Speed (tok/s)
Gemini 3.5 Flash (high)	50.2	265.599
Gemini 3.6 Flash (high)	50.1	255.299
Gemini 3.1 Pro Preview	46.5	146.529
Gemini 3.5 Flash (medium)	45.4	275.345
Gemini 3 Pro Preview (high)	39.6	0
Gemini 3 Flash Preview (Reasoning)	37.8	0
Gemini 3.5 Flash-Lite	36.5	404.171
Gemini 3.5 Flash (minimal)	34.9	256.927
Gemini 3 Pro Preview (low)	33.1	0
Gemma 4 31B (Reasoning)	29.4	35.492
Gemini 3 Flash Preview (Non-reasoning)	27.4	0
Gemini 2.5 Pro	25.8	153.192
Gemma 4 26B A4B (Reasoning)	25.7	0
Gemini 3.1 Flash-Lite	25	334.209
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	23.8	0
Gemini 2.5 Pro Preview (Mar' 25)	23	0
Gemini 2.5 Pro Preview (May' 25)	22.3	0
Gemma 4 31B (Non-reasoning)	21.8	75.181
Gemma 4 12B (Reasoning)	21.8	128.009
Gemma 4 26B A4B (Non-reasoning)	20.1	68.754
Gemini 2.5 Flash (Reasoning)	20.1	0
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	18.8	0
Gemini 2.5 Flash Preview (Reasoning)	17.5	0
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	15.1	0
Gemini 2.5 Flash (Non-reasoning)	14.1	0
DiffusionGemma 26B A4B	13.5	0
Gemini 2.0 Flash Thinking Experimental (Jan '25)	13.3	0
Gemma 4 12B (Non-reasoning)	13.2	119.5
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	13.1	0
Gemini 2.0 Flash (Feb '25)	12.3	0
Gemma 4 E4B (Reasoning)	11.9	105.808
Gemini 2.0 Pro Experimental (Feb '25)	11.8	0
Gemini 2.5 Flash Preview (Non-reasoning)	11.7	0
Gemini 2.5 Flash-Lite (Reasoning)	11.4	0
Gemini 2.0 Flash (experimental)	10.7	0
Gemini 1.5 Pro (Sep '24)	10	0
Gemma 4 E2B (Reasoning)	9.4	0
Gemma 4 E4B (Non-reasoning)	8.9	112.425
Gemini 2.0 Flash-Lite (Feb '25)	8.8	0
Gemini 2.0 Flash-Lite (Preview)	8.6	0

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models