RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

What AI models run on the RTX 5060 Ti 16GB?

The RTX 5060 Ti 16GB has 16 GB of VRAM (448 GB/s). About 15.2 GB is usable for a model. 194 of 285 open models we track fit at 8K context.

194models fit (8K ctx)
180still fit at 32K ctx
40Blargest that fits
448 GB/smemory bandwidth

This card has 16 GB of VRAM. See every model that fits in 16 GB VRAM. Other 16 GB hardware: RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080, RTX 4080 Super, RTX 5070 Ti, RTX 5080, RX 7800 XT, RX 7900 GRE.

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)
flint40B (1.3B act.)Q2_K14.8 GBno956details
Maxwell V1 Flash37B (2.3B act.)Q2_K14.0 GBQ2_K526details
Qwen3.6 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K398details
Ornith 1.5 35B A3B36B (3.0B act.)Q2_K13.2 GBQ2_K410details
Qwen3.5 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K398details
Axion 1.0 35B35B (3.9B act.)Q2_K13.3 GBQ2_K306details
Qwen AgentWorld 35B A3B35B (3.0B act.)Q2_K13.1 GBQ2_K398details
Yi 1.5 34B Chat34BQ2_K14.3 GBno35details
Nous Hermes 2 Yi 34B34BQ2_K14.8 GBno34details
DeepSeek R1 Distill Qwen 32B33BQ2_K14.2 GBno36details
Qwen3 32B33BQ2_K14.1 GBno36details
GLM Z1 32B 041433BQ2_K12.6 GBQ2_K36details
GLM 4 32B 041433BQ2_K12.6 GBQ2_K36details
granite 4.0 h small32B (8.8B act.)Q2_K11.7 GBQ2_K139details
gemma 4 31B it31BQ2_K13.9 GBno38details
GLM 4.7 Flash31B (4.6B act.)Q2_K11.7 GBQ2_K268details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)Q2_K11.9 GBQ2_K405details
North Mini Code 1.030B (3.3B act.)Q2_K12.0 GBQ2_K361details
Hy Memory 30B A3B30B (3.0B act.)Q2_K11.9 GBQ2_K398details
Muse Glimmer 30B30BQ2_K11.4 GBQ2_K40details
granite 4.2 30b29BQ2_K12.7 GBno41details
Qwen3.8 27B28BQ2_K11.1 GBQ2_K43details
Qwen3.6 27B28BQ2_K11.1 GBQ2_K43details
Qwen3.5 27B28BQ2_K11.1 GBQ2_K43details
gemma 3 27b it27BQ2_K11.7 GBQ2_K43details
Arete 27B27BQ3_K_M13.6 GBQ2_K34details
MiniMax H3 Image PE27BQ2_K11.3 GBQ2_K42details
Trinity Mini26B (2.0B act.)Q3_K_M12.3 GBQ3_K_M492details
GLiDE 27B26BQ3_K_M13.2 GBQ2_K35details
diffusiongemma 26B A4B it26B (4.0B act.)Q3_K_M13.2 GBQ2_K229details
gemma 4 26B A4B it26B (4.0B act.)Q3_K_M13.3 GBQ2_K227details
LFM2.5 24B A2B24B (2.0B act.)Q3_K_M11.7 GBQ3_K_M458details
ERNIE 4.5 21B A3B PT22BQ4_K_M13.5 GBQ3_K_M34details
ERNIE 4.5 21B A3B Thinking22BQ4_K_M13.5 GBQ3_K_M34details
gpt oss safeguard 20b22B (4.8B act.)Q8_012.3 GBQ8_0166details
gpt oss 20b21B (4.2B act.)Q8_012.3 GBQ8_0185details
Groot 19B A3B 26102319B (3.0B act.)Q4_K_M12.7 GBQ4_K_M232details
Kimi VL A3B Thinking 250616B (3.0B act.)Q6_K13.5 GBQ5_K_M182details
Kimi VL A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M203details
Kimi VL A3B Thinking16B (3.0B act.)Q6_K13.5 GBQ5_K_M182details
deepseek moe 16b base16B (2.8B act.)Q4_K_M12.5 GBQ2_K239details
LLaDA2.1 mini16B (1.4B act.)Q6_K13.4 GBQ5_K_M381details
Moonlight 16B A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M198details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M223details
DeepSeek V2 Lite16B (2.7B act.)Q5_K_M11.3 GBQ5_K_M236details
DeepSeek V2 Lite Chat16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M223details
Qwen2.5 Coder 14B Instruct15BQ6_K13.5 GBQ3_K_M37details
DeepSeek R1 Distill Qwen 14B15BQ6_K13.5 GBQ3_K_M37details
Qwen3 14B15BQ6_K13.2 GBQ3_K_M37details
phi 415BQ6_K13.4 GBQ3_K_M37details
gemma 3 12b it12BQ8_013.4 GBQ6_K36details
Llama Guard 4 12B12BQ6_K11.5 GBQ4_K_M46details
Llama 3.2 11B Vision Instruct11BQ8_011.6 GBQ5_K_M43details
Llama 3.2 11B Vision11BQ8_012.4 GBQ5_K_M40details
GLM 4.6V Flash10BQ8_010.3 GBQ8_045details
GLM 4.1V 9B Thinking10BQ8_010.3 GBQ8_045details
Step3 VL 10B10BQ8_09.9 GBQ8_051details
SenseNova Loop 9B Preview9.7BQ8_010.0 GBQ8_047details
Qwen3.5 9B9.7BQ8_010.0 GBQ8_047details
Ornith 1.5 9B9.7BQ8_010.0 GBQ8_047details
Qwen3.5 9B Base9.7BQ8_010.0 GBQ8_047details
MiMo V2.6 Distill Qwen 9B9.4BQ8_010.0 GBQ8_047details
glm 4 9b9.4BQ6_K13.4 GBno54details
internlm3 8b instruct8.8BQ8_09.7 GBQ8_048details
granite 4.2 8b8.8BQ8_010.5 GBQ6_K48details
granite 4.1 8b8.8BQ8_010.5 GBQ6_K48details
Qwen3 VL 8B Instruct8.8BQ8_09.9 GBQ8_051details
Molmo2 8B8.7BQ8_09.9 GBQ8_051details
LFM2.5 8B A1B8.5B (1.0B act.)Q8_09.1 GBQ8_0421details
Qwen2.5 VL 7B Instruct8.3BQ8_08.7 GBQ8_055details
UI TARS 1.5 7B8.3BQ8_08.7 GBQ8_055details
olmOCR 2 7B 10258.3BQ8_08.7 GBQ8_055details
olmOCR 7B 0225 preview8.3BQ8_08.7 GBQ8_055details
UI TARS 7B DPO8.3BQ8_08.7 GBQ8_055details
Qwen3 8B8.2BQ8_09.9 GBQ8_051details
DeepSeek R1 0528 Qwen3 8B8.2BQ8_09.9 GBQ8_051details
granite 3.3 8b instruct8.2BQ8_09.8 GBQ8_052details
granite 3.1 8b instruct8.2BQ8_09.8 GBQ8_052details
granite 3.2 8b instruct8.2BQ8_09.8 GBQ8_052details
Apertus 8B Instruct 25098.1BQ8_09.6 GBQ8_052details
Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_053details
Llama 3.1 8B8.0BQ8_09.6 GBQ8_052details
Hermes 3 Llama 3.1 8B8.0BQ8_09.6 GBQ8_052details
DeepSeek R1 Distill Llama 8B8.0BQ8_09.6 GBQ8_052details
Meta Llama 3 8B Instruct8.0BQ8_09.6 GBQ8_052details
Meta Llama Guard 2 8B8.0BQ8_09.6 GBQ8_052details
Meta Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_052details
Ling 3.0 tiny7.9B (1.4B act.)Q8_08.7 GBQ8_0304details
MiMo 7B RL7.8BQ8_09.4 GBQ8_055details
internlm2 5 7b chat7.7BQ8_09.2 GBQ8_054details
internlm2 chat 7b7.7BQ8_09.2 GBQ8_054details
Qwen2.5 7B Instruct7.6BQ8_08.7 GBQ8_055details
Qwen2.5 Coder 7B Instruct7.6BQ8_08.7 GBQ8_055details
DeepSeek R1 Distill Qwen 7B7.6BQ8_08.7 GBQ8_055details
Falcon H1R 7B7.6BQ8_08.5 GBQ8_056details
Olmo 3 7B Instruct7.3BQ8_010.3 GBQ8_058details
Olmo 3 1025 7B7.3BQ8_010.3 GBQ8_058details
Olmo 3 7B Think7.3BQ8_010.3 GBQ8_058details
Mistral 7B v0.17.2BQ8_08.6 GBQ8_058details
Mistral 7B Instruct v0.27.2BQ8_08.6 GBQ8_058details
Mistral 7B Instruct v0.17.2BQ8_08.6 GBQ8_058details
falcon 7b7.2BQ8_012.1 GBno58details
falcon 7b instruct7.2BQ8_011.8 GBno61details
granite 4.0 h tiny6.9B (1.5B act.)F1613.6 GBQ8_0153details
OLMoE 1B 7B 09246.9B (1.3B act.)Q8_08.4 GBQ8_0329details
deepseek coder 7b instruct v1.56.9BQ8_011.2 GBno61details
deepseek coder 6.7b instruct6.7BQ8_011.1 GBno63details
deepseek coder 6.7b base6.7BQ8_011.1 GBno63details
Llama 2 7b hf6.7BQ8_011.1 GBno63details
Yi 6B 200K6.1BF1612.3 GBQ8_037details
Yi 6B6.1BF1612.3 GBQ8_037details
Molmo2 4B4.9BF1610.0 GBF1651details
WeVisOne VL 4B4.8BF1610.0 GBF1651details
Mage VL Cowork4.7BF1610.0 GBF1651details
Qianfan OCR4.7BF1610.1 GBF1651details
Qwen3.5 4B4.7BF169.0 GBF1653details
S5 nano4.7BF169.2 GBF1652details
LightOnOCR 3 4B4.5BF169.0 GBF1653details
SingVL S1 4B4.5BF169.0 GBF1653details
Intern Decision 4B4.5BF169.0 GBF1653details
Qwen3 VL 4B Instruct4.4BF169.3 GBF1656details
gemma 3 4b it4.3BF168.4 GBF1658details
medgemma 1.5 4b it4.3BF168.4 GBF1658details
medgemma 4b it4.3BF168.4 GBF1658details
gemma 3 4b pt4.3BF169.2 GBF1652details
Phi 3.5 vision instruct4.1BF1611.2 GBQ4_K_M54details
Qwen3 4B4.0BF169.3 GBF1656details
Qwen3 4B Instruct 25074.0BF169.3 GBF1656details
granite vision 4.1 4b4.0BF167.6 GBF1666details
Phi 4 mini instruct3.8BF168.9 GBF1658details
Phi 3 mini 4k instruct3.8BF1610.6 GBQ5_K_M59details
Phi 3.5 mini instruct3.8BF1610.6 GBQ5_K_M59details
Phi 3 mini 128k instruct3.8BF1610.6 GBQ5_K_M59details
Qwen2.5 VL 3B Instruct3.8BF166.7 GBF1673details
granite 4.2 3b3.7BF168.0 GBF1661details
granite 4.1 3b llmon preview3.7BF168.0 GBF1661details
Raon 1 nano3.5BF167.0 GBF1671details
granite 4.1 3b3.4BF167.6 GBF1666details
granite 4.0 micro3.4BF167.6 GBF1666details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16216details
deepseek vl2 tiny3.4B (1.2B act.)F167.4 GBF16191details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16222details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16223details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16223details
granite 3.1 3b a800m instruct3.3B (883M act.)F167.1 GBF16253details
Llama 3.2 3B Instruct3.2BF1613.5 GBQ8_035details
Llama 3.2 3B3.2BF167.5 GBF1670details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF1670details
d1 3B3.1BF1610.8 GBF1641details
LFM2.5 VL 3B3.1BF1610.8 GBF1641details
Qwen2.5 3B Instruct3.1BF166.7 GBF1673details
SmolLM3 3B3.1BF166.9 GBF1673details
SmolLM3 3B Base3.1BF166.9 GBF1673details
phi 22.8BF168.2 GBQ8_081details
LFM2.5 2.6B2.7BF1610.8 GBF1641details
granite 3.3 2b instruct2.5BF165.8 GBF1688details
MiniCPM5 2B2.5BF165.7 GBF1689details
WeVisOne VL 2B2.4BF165.4 GBF16110details
Qwen3.5 2B2.3BF164.5 GBF16119details
SmolVLM Instruct2.2BF165.4 GBF16124details
Qwen3 1.7B2.0BF164.8 GBF16130details
Qwen3.8 27B DSpine b162.0BF164.8 GBF16110details
d1 2B1.9BF167.2 GBF1665details
LFM3 VL 2B1.9BF167.2 GBF1665details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF16126details
LFM3 1.7B1.7BF167.2 GBF1665details
LFM3 1.7B Base1.7BF164.0 GBF16130details
SmolLM2 1.7B Instruct1.7BF165.2 GBF16131details
SmolLM2 1.7B1.7BF165.2 GBF16131details
SmolLM 1.7B1.7BF165.2 GBF16131details
granite 4.0 1b1.6BF164.3 GBF16137details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF16145details
OLMo 2 0425 1B1.5BF164.4 GBF16151details
deepseek coder 1.3b instruct1.3BF164.5 GBF16166details
Llama 3.2 1B1.2BF163.2 GBF16181details
Llama 3.2 1B Instruct1.2BF165.5 GBF1690details
LFM2.5 1.2B Instruct1.2BF165.0 GBF1696details
HunyuanOCR1.1BF163.5 GBF16200details
PaddleOCR VL 1.6959MF162.5 GBF16234details
Qwen3.5 0.8B873MF162.4 GBF16295details
LightOnOCR 3 0.8B853MF162.4 GBF16295details
FastVLM 0.5B759MF162.2 GBF16295details
Qwen3 0.6B752MF162.7 GBF16374details
GOT OCR2 0716MF162.8 GBF16313details
Nemotron 3.5 Parse631MF161.9 GBF16343details
GOT OCR 2.0 hf561MF162.5 GBF16400details
SmolVLM2 500M Video Instruct507MF161.6 GBF16546details
SmolVLM 500M Instruct507MF161.6 GBF16546details
Qwen2.5 0.5B Instruct494MF161.7 GBF16453details
LFM2.5 VL 450M449MF161.9 GBF16315details
SmolLM2 360M Instruct362MF161.5 GBF16617details
SmolLM2 360M362MF161.5 GBF16617details
LFM2.5 350M354MF161.9 GBF16315details
LFM2 350M354MF161.4 GBF16632details

Just too big at 4-bit

These need up to 35% more memory than the RTX 5060 Ti 16GB has at Q4_K_M and 8K context. A smaller quant or shorter context may work.

ModelQ4_K_M needsShort by
Trinity Mini15.8 GB0.6 GB
GLiDE 27B16.2 GB1.0 GB
MiniMax H3 Image PE16.8 GB1.6 GB
Qwen3.8 27B16.8 GB1.6 GB
Qwen3.5 27B17.0 GB1.8 GB
Qwen3.6 27B17.0 GB1.8 GB
diffusiongemma 26B A4B it17.1 GB1.9 GB
gemma 4 26B A4B it17.2 GB2.0 GB
gemma 3 27b it17.3 GB2.1 GB
Arete 27B17.4 GB2.2 GB
Muse Glimmer 30B17.9 GB2.7 GB
GLM 4.7 Flash18.2 GB3.0 GB
Hy Memory 30B A3B18.5 GB3.3 GB
Qwen3 Coder 30B A3B Instruct18.7 GB3.5 GB
granite 4.0 h small18.9 GB3.7 GB

Questions

What is the biggest model that runs on the RTX 5060 Ti 16GB?

Of the models we track, the largest that fits at 8K context is flint (40B) at Q2_K, needing about 14.8 GB.

How much of the RTX 5060 Ti 16GB's memory can a model use?

About 15.2 GB: we assume 95% of the 16 GB is usable after driver and display overhead.

Spec source: NVIDIA specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.