RTX 3060 x2

Nvidia · 12 GB VRAM

31recorded runs

198.1best tok/s

29sourced

Evidence: 29 sourced runs · 2 awaiting review · 1 independent source · first recorded May 28, 2026 · last recorded Aug 29, 2026. What these labels mean.

What fits on 12 GB — measured

Model	Quant	Peak VRAM	Headroom
gemma-4-31B-it	Q4_K_M	21.7 GB	-9.7 GB
Olmo-3-32B-Think	Q4_K_M	21.0 GB	-9.0 GB
Qwen3-30B-A3B-Thinking-2507	Q4_K_M	20.1 GB	-8.1 GB
GLM-Z1-32B-0414	Q4_K_M	19.8 GB	-7.8 GB
DeepHermes-3-Mistral-24B-Preview	Q4_K_M	19.5 GB	-7.5 GB
Tess-4-27B	Q4_K_M	19.4 GB	-7.4 GB
Muse-Glimmer-30B	UD-Q4_K_XL	18.7 GB	-6.7 GB
reka-flash-3	Q4_K_M	18.5 GB	-6.5 GB

Peak process memory recorded by the submitter on this card — evidence of what fit, not a guarantee. Plan with the VRAM calculator.

All benchmarks Compare RTX 3060 x2 →

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 3060 x2 · 12 GB	Qwen3-1.7B	Q4_K_M	llama.cpp 13f2b28	512	198.1 ✓	7121.2	6.7	src
RTX 3060 x2 · 12 GB	MiniCPM5-1B	Q4_K_M	llama.cpp 2cbfdc6	128000	125.9 ✓	14828.4	4.3	src
RTX 3060 x2 · 12 GB	Trinity-Mini	Q4_K_M	llama.cpp 13f2b28	512	109.0 ✓	1956.3	16.6	src
RTX 3060 x2 · 12 GB	Phi-4-mini-reasoning	Q4_K_M	llama.cpp 13f2b28	512	108.2 ✓	3875.2	8.6	src
RTX 3060 x2 · 12 GB	gemma-4-26B-A4B-it-qat	Q4_K_M	llama.cpp 13f2b28	512	95.3 ✓	1962.1	16.0	src
RTX 3060 x2 · 12 GB	Qwen3-30B-A3B-Thinking-2507	Q4_K_M	llama.cpp b10443	65536	94.3 ✓	1073.4	20.1	src
RTX 3060 x2 · 12 GB	gpt-oss-20b	Q4_K_M	llama.cpp b10443	65536	93.4 ✓	895.4	12.2	src
RTX 3060 x2 · 12 GB	OpenReasoning-Nemotron-7B	Q4_K_M	llama.cpp 13f2b28	512	68.0 ✓	2264.1	7.3	src
RTX 3060 x2 · 12 GB	WebWorld-8B	Q4_K_M	llama.cpp 2d97363	512	62.3 ✓	1976.2	6.3	src
RTX 3060 x2 · 12 GB	gemma-4-26B-A4B-it	UD-Q4_K_M	llama.cpp b10443	65536	62.1 ✓	794.6	18.0	src
RTX 3060 x2 · 12 GB	Carnice-9b	Q4_K_M	llama.cpp 2d97363	512	56.1 ✓	1621.8	6.7	src
RTX 3060 x2 · 12 GB	Muse-Glimmer-30B	UD-Q4_K_XL	llama.cpp b10443	65536	56.0 ✓	634.6	18.7	src
RTX 3060 x2 · 12 GB	NVIDIA-Nemotron-Nano-12B-v2	Q4_K_M	llama.cpp 13f2b28	512	40.4 ✓	1016.0	9.9	src
RTX 3060 x2 · 12 GB	gemma-3-12b-it	Q4_K_M	llama.cpp 2d97363	512	39.4 ✓	1275.9	8.5	src
RTX 3060 x2 · 12 GB	Qwen3-14B	Q4_K_M	llama.cpp 13f2b28	512	35.8 ✓	1136.8	15.4	src
RTX 3060 x2 · 12 GB	Nemotron-Cascade-14B-Thinking	Q4_K_M	llama.cpp 13f2b28	512	35.7 ✓	1140.0	15.4	src
RTX 3060 x2 · 12 GB	Phi-4-reasoning	Q4_K_M	llama.cpp 13f2b28	512	35.4 ✓	1153.9	17.2	src
RTX 3060 x2 · 12 GB	WebWorld-14B	Q4_K_M	llama.cpp 2d97363	512	35.4 ✓	1115.6	10.0	src
RTX 3060 x2 · 12 GB	InternVL3-14B	Q4_K_M	llama.cpp 13f2b28	512	35.1 ✓	1115.8	0.1	src
RTX 3060 x2 · 12 GB	DeepSeek-R1-Distill-Qwen-14B	Q4_K_M	llama.cpp 13f2b28	512	35.1 ✓	1123.3	16.5	src
RTX 3060 x2 · 12 GB	phi-4	Q4_K_M	llama.cpp b10443	16384	34.2 ✓	889.5	9.8	src
RTX 3060 x2 · 12 GB	DeepHermes-3-Mistral-24B-Preview	Q4_K_M	llama.cpp 13f2b28	512	24.5 ✓	825.2	19.5	src
RTX 3060 x2 · 12 GB	reka-flash-3	Q4_K_M	llama.cpp 13f2b28	512	23.9 ✓	834.6	18.5	src
RTX 3060 x2 · 12 GB	mistralai_Mistral-Small-3.2-24B-Instruct-2506	Q4_K_M	llama.cpp b10443	65536	21.8 ✓	586.5	17.4	src
RTX 3060 x2 · 12 GB	Qwen3.6-27B	IQ4_NL	llama.cpp b10443	32768	18.9 ✓	339.8	—	src
RTX 3060 x2 · 12 GB	Tess-4-27B	Q4_K_M	llama.cpp 13f2b28	512	18.8 ✓	523.7	19.4	src
RTX 3060 x2 · 12 GB	GLM-Z1-32B-0414	Q4_K_M	llama.cpp 13f2b28	512	16.6 ✓	532.5	19.8	src
RTX 3060 x2 · 12 GB	Olmo-3-32B-Think	Q4_K_M	llama.cpp 13f2b28	512	16.4 ✓	513.0	21.0	src
RTX 3060 x2 · 12 GB	gemma-4-31B-it	Q4_K_M	llama.cpp b10443	65536	15.8 ✓	578.2	21.7	src
RTX 3060 x2 · 12 GB	Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp —	90112	129.4 …	—	—	src
RTX 3060 x2 · 12 GB	Qwen3.8-27B	UD-Q4_K_XL	llama.cpp —	65536	57.0 …	—	—	src

Related reading: GPU buying guide · used GPUs · Value index · Street prices