Skip to content

What can the RTX 4070 Ti Super run?

What fits on the RTX 4070 Ti Super
Text models: 247Visual models: 18Strongest first
Memory
16 GB
Bandwidth
672 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 4070 Ti Super, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 27B3-bit20K34 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B3-bit40K32 tok/sDocs
Gemma 4 26B A4B3-bit224K174 tok/sChat, Coding, Agents, Docs
Qwen3.5 9B8-bit144K49 tok/sChat, Coding, Agents, Docs
Gemma 4 12B8-bit248K35 tok/sChat, Coding, Docs
Qwen3.5 4B8-bit256K86 tok/sAgents, Docs
Devstral Small 2 24B3-bit20K39 tok/sCoding
LFM2.5 24B A2B4-bit44K201 tok/sAgents
Mistral Small 3.2 24B3-bit20K39 tok/sChat, Coding, Agents
Ministral 3 14B6-bit20K41 tok/sCoding, Agents, Docs
Gemma 4 E4B8-bit128K77 tok/sChat, Coding, Docs
gpt-oss 20BMXFP4120K145 tok/sAgents
Ministral 3 8B8-bit40K50 tok/sDocs
Gemma 4 E2B8-bit128K137 tok/sChat
Nemotron 3 Nano 4B8-bit256K106 tok/sDocs
Llama 3.1 8B8-bit48K56 tok/sChat, Coding, Agents, Docs
Qwen3 0.6B8-bit40K394 tok/sNot rated
Qwen3 14B6-bit16K39 tok/sNot rated
Qwen3 VL 8B Instruct8-bit40K51 tok/sText and images
Qwen3 8B8-bit40K55 tok/sNot rated
Qwen2.5 7B Instruct8-bit32K59 tok/sNot rated
Qwen2.5 VL 7B Instruct8-bit112K55 tok/sText and images
Unlimited OCR8-bit32K303 tok/sReading documents
Qwen3 VL 4B Instruct8-bit64K90 tok/sText and images
Qwen3 1.7B8-bit40K184 tok/sNot rated
Qwen3 4B8-bit40K98 tok/sNot rated
Qwen3 4B Instruct 25078-bit72K98 tok/sNot rated
Qwen2.5 3B Instruct8-bit32K124 tok/sNot rated
Qwen3.6 27B3-bit20K34 tok/sText and images
DeepSeek OCR8-bit8K303 tok/sReading documents
Qwen2.5 Coder 14B Instruct6-bit16K39 tok/sCoding
Qwen2.5 VL 3B Instruct8-bit125K105 tok/sText and images
Qwen3.5 27B3-bit20K34 tok/sText and images
Qwen2.5 Coder 7B Instruct8-bit32K59 tok/sCoding
Mistral 7B Instruct V0.28-bit32K59 tok/sNot rated
Chandra OCR 28-bit256K77 tok/sReading documents
Qwen3 VL 2B Instruct8-bit112K177 tok/sText and images
MiniCPM5 2B8-bit128K158 tok/sNot rated
Gemma 3 4B IT8-bit128K109 tok/sText and images
Llama 3.2 3B Instruct8-bit96K124 tok/sNot rated
Qwen2.5 14B Instruct6-bit16K39 tok/sNot rated
Qwen3 1.7B Base8-bit32K212 tok/sNot rated
Diffusiongemma 26B A4B IT3-bit112K168 tok/sText and images
HunyuanOCR8-bit128K308 tok/sText and images
Qwen3 0.6B Base8-bit32K457 tok/sNot rated
Qwen2 VL 7B Instruct8-bit32K55 tok/sText and images
Ornith 1.5 9B8-bit144K49 tok/sNot rated
Unlimited OCR 28-bit128K302 tok/sReading documents
Granite 4.1 3B8-bit128K113 tok/sNot rated
Mistral 7B V0.18-bit32K59 tok/sNot rated
Qwen2.5 Coder 3B Instruct8-bit32K124 tok/sCoding
Meta Llama 3 8B Instruct Abliterated V38-bit8K56 tok/sNot rated
EXAONE 3.5 7.8B Instruct8-bit32K57 tok/sNot rated
Saiga Llama3 8B8-bit8K56 tok/sNot rated
DeepSeek R1 0528 Qwen3 8B8-bit44K55 tok/sNot rated
Gemma 3 12B IT8-bit28K37 tok/sText and images
Phi 3.5 Mini Instruct8-bit28K107 tok/sNot rated
Qwen3 4B Thinking 25078-bit72K98 tok/sNot rated
Phi 4 Mini Instruct8-bit80K104 tok/sNot rated
Dots.ocr8-bit128K139 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 4070 Ti Super
ModelBest fitPer outputStrongest at
LTX-2.55-bit1.6 minVideo
Z-Image Turbo16-bit11 sImages
FLUX.1 [dev]8-bit21 sImages
Qwen-Image5-bit7.5 minImages
Qwen-Image 2.116-bit2.8 minImages
FLUX.3 Klein16-bit16 sImages
Wan2.2 I2V A14B4-bit66 minVideo
FLUX.2 [klein] 9B8-bit5.7 sImages
Wan2.1 I2V 14B4-bit66 minVideo
Wan 2.1 T2V-14B4-bit83 minVideo
Krea 2 Turbo8-bit21 sImages
Stable Diffusion 3.5 Large8-bit89 sImages
Qwen Image 25125-bit7.5 minImages
MOSS-Image16-bit1.8 minImages
Wan 2.2 TI2V-5B16-bit16 minVideo
MOSS Image Base16-bit1.8 minImages
Wan 2.2 A14B4-bit66 minVideo
HunyuanVideo 1.58-bit71 minVideo

Only just too big

Questions

What is the best LLM for the RTX 4070 Ti Super?

Of the open models we track, the strongest that run well on the RTX 4070 Ti Super 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