Skip to content

What can the RTX 4060 Ti 16 GB run?

What fits on the RTX 4060 Ti 16 GB
Text models: 247Visual models: 18Strongest first
Memory
16 GB
Bandwidth
288 GB/s
Maker
NVIDIA

Open the calculator on this machineEvery model for 16 GB of VRAM

Text models that run on it

Text models that run on the RTX 4060 Ti 16 GB, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 27B3-bit20K15 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B3-bit40K14 tok/sDocs
Gemma 4 26B A4B3-bit224K91 tok/sChat, Coding, Agents, Docs
Qwen3.5 9B8-bit144K21 tok/sChat, Coding, Agents, Docs
Gemma 4 12B8-bit248K16 tok/sChat, Coding, Docs
Qwen3.5 4B8-bit256K39 tok/sAgents, Docs
Devstral Small 2 24B3-bit20K17 tok/sCoding
LFM2.5 24B A2B4-bit44K119 tok/sAgents
Mistral Small 3.2 24B3-bit20K17 tok/sChat, Coding, Agents
Ministral 3 14B6-bit20K18 tok/sCoding, Agents, Docs
Gemma 4 E4B8-bit128K35 tok/sChat, Coding, Docs
gpt-oss 20BMXFP4120K71 tok/sAgents
Ministral 3 8B8-bit40K22 tok/sDocs
Gemma 4 E2B8-bit128K64 tok/sChat
Nemotron 3 Nano 4B8-bit256K49 tok/sDocs
Llama 3.1 8B8-bit48K25 tok/sChat, Coding, Agents, Docs
Qwen3 0.6B8-bit40K208 tok/sNot rated
Qwen3 14B6-bit16K17 tok/sNot rated
Qwen3 VL 8B Instruct8-bit40K23 tok/sText and images
Qwen3 8B8-bit40K24 tok/sNot rated
Qwen2.5 7B Instruct8-bit32K26 tok/sNot rated
Qwen2.5 VL 7B Instruct8-bit112K24 tok/sText and images
Unlimited OCR8-bit32K149 tok/sReading documents
Qwen3 VL 4B Instruct8-bit64K41 tok/sText and images
Qwen3 1.7B8-bit40K87 tok/sNot rated
Qwen3 4B8-bit40K45 tok/sNot rated
Qwen3 4B Instruct 25078-bit72K45 tok/sNot rated
Qwen2.5 3B Instruct8-bit32K58 tok/sNot rated
Qwen3.6 27B3-bit20K15 tok/sText and images
DeepSeek OCR8-bit8K149 tok/sReading documents
Qwen2.5 Coder 14B Instruct6-bit16K17 tok/sCoding
Qwen2.5 VL 3B Instruct8-bit125K48 tok/sText and images
Qwen3.5 27B3-bit20K15 tok/sText and images
Qwen2.5 Coder 7B Instruct8-bit32K26 tok/sCoding
Mistral 7B Instruct V0.28-bit32K26 tok/sNot rated
Chandra OCR 28-bit256K34 tok/sReading documents
Qwen3 VL 2B Instruct8-bit112K83 tok/sText and images
MiniCPM5 2B8-bit128K76 tok/sNot rated
Gemma 3 4B IT8-bit128K50 tok/sText and images
Llama 3.2 3B Instruct8-bit96K56 tok/sNot rated
Qwen2.5 14B Instruct6-bit16K17 tok/sNot rated
Qwen3 1.7B Base8-bit32K101 tok/sNot rated
Diffusiongemma 26B A4B IT3-bit112K87 tok/sText and images
HunyuanOCR8-bit128K151 tok/sText and images
Qwen3 0.6B Base8-bit32K251 tok/sNot rated
Qwen2 VL 7B Instruct8-bit32K24 tok/sText and images
Ornith 1.5 9B8-bit144K21 tok/sNot rated
Unlimited OCR 28-bit128K148 tok/sReading documents
Granite 4.1 3B8-bit128K52 tok/sNot rated
Mistral 7B V0.18-bit32K26 tok/sNot rated
Qwen2.5 Coder 3B Instruct8-bit32K58 tok/sCoding
Meta Llama 3 8B Instruct Abliterated V38-bit8K25 tok/sNot rated
EXAONE 3.5 7.8B Instruct8-bit32K25 tok/sNot rated
Saiga Llama3 8B8-bit8K25 tok/sNot rated
DeepSeek R1 0528 Qwen3 8B8-bit44K24 tok/sNot rated
Gemma 3 12B IT8-bit28K17 tok/sText and images
Phi 3.5 Mini Instruct8-bit28K49 tok/sNot rated
Qwen3 4B Thinking 25078-bit72K45 tok/sNot rated
Phi 4 Mini Instruct8-bit80K47 tok/sNot rated
Dots.ocr8-bit128K64 tok/sReading documents

Best fit is the highest quality, up to 8-bit, that leaves the use case’s context. Ranked by our use-case scores, then by Hugging Face downloads. Speeds are rough, plus or minus 25%. The top 60 of 247 are shown.

Image and video models

Image and video models that run on the RTX 4060 Ti 16 GB
ModelBest fitPer outputStrongest at
LTX-2.55-bit2.8 minVideo
Z-Image Turbo16-bit21 sImages
FLUX.1 [dev]8-bit41 sImages
Qwen-Image5-bit15 minImages
Qwen-Image 2.116-bit5.6 minImages
FLUX.3 Klein16-bit31 sImages
Wan2.2 I2V A14B4-bit2.2 hVideo
FLUX.2 [klein] 9B8-bit10 sImages
Wan2.1 I2V 14B4-bit2.2 hVideo
Wan 2.1 T2V-14B4-bit2.8 hVideo
Krea 2 Turbo8-bit41 sImages
Stable Diffusion 3.5 Large8-bit2.9 minImages
Qwen Image 25125-bit15 minImages
MOSS-Image16-bit3.7 minImages
Wan 2.2 TI2V-5B16-bit31 minVideo
MOSS Image Base16-bit3.7 minImages
Wan 2.2 A14B4-bit2.2 hVideo
HunyuanVideo 1.58-bit2.3 hVideo

Only just too big

Questions

What is the best LLM for the RTX 4060 Ti 16 GB?

Of the open models we track, the strongest that run well on the RTX 4060 Ti 16 GB are Qwen3.8 27B, Muse Glimmer 30B, Gemma 4 26B A4B. 247 text models fit it in all.

Calculated from published specs, not benchmarked. All machines