RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

What AI models run on the RTX 4070 Ti Super?

The RTX 4070 Ti Super has 16 GB of VRAM (672 GB/s). About 15.2 GB is usable for a model. 200 of 298 open models we track fit at 8K context.

200models fit (8K ctx)
189still fit at 32K ctx
37Blargest that fits
672 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 4080, RTX 4080 Super, RTX 5060 Ti 16GB, RTX 5070 Ti, RTX 5080, RX 7800 XT, RX 7900 GRE.

Compare for local LLMs: RTX 4070 Ti Super vs RTX 4070 SuperRTX 4070 Ti Super vs RTX 5070 TiRTX 4070 Ti Super vs RTX 3090RTX 4070 Ti Super vs RX 7900 XT all comparisons

Using a specific tool? Ollama models that run on the RTX 4070 Ti Super · LM Studio · llama.cpp offload

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)Details
Maxwell V1 Flash37B (2.3B act.)Q2_K14.0 GBQ2_K789details
Qwen3.6 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K596details
Ornith 1.5 35B A3B36B (3.0B act.)Q2_K13.2 GBQ2_K615details
Qwen3.5 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K596details
Sage A1.536B (4.7B act.)Q2_K13.4 GBQ2_K384details
Qwen AgentWorld 35B A3B35B (3.0B act.)Q2_K13.1 GBQ2_K597details
Yi 1.5 34B Chat34BQ2_K14.3 GBno52details
Nous Hermes 2 Yi 34B34BQ2_K14.8 GBno50details
DeepSeek R1 Distill Qwen 32B33BQ2_K14.2 GBno55details
Qwen3 32B33BQ2_K14.1 GBno55details
GLM Z1 32B 041433BQ2_K12.5 GBQ2_K55details
GLM 4 32B 041433BQ2_K12.6 GBQ2_K55details
Olmo 3 32B Think32BQ2_K13.0 GBQ2_K56details
Granite 4.0 H Small32B (8.8B act.)Q2_K11.7 GBQ2_K209details
Gemma 4 31B IT31BQ2_K14.7 GBno53details
Gemma 4 31B31BQ2_K13.9 GBno57details
GLM 4.7 Flash31B (4.6B act.)Q2_K11.4 GBQ2_K412details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)Q2_K12.1 GBQ2_K597details
North Mini Code 1.030B (3.3B act.)Q2_K11.7 GBQ2_K559details
Hy Memory 30B A3B30B (3.0B act.)Q2_K11.9 GBQ2_K597details
Muse Glimmer 30B30BQ2_K11.4 GBQ2_K60details
Granite 4.2 30B29BQ2_K12.7 GBno62details
Raon 1 Mini Preview29B (4.3B act.)Q2_K11.2 GBQ2_K415details
Qwen3.8 27B28BQ2_K11.5 GBQ2_K62details
Qwen3.6 27B28BQ2_K12.6 GBQ2_K56details
Qwen3.5 27B28BQ2_K12.6 GBQ2_K56details
Gemma 3 27B IT27BQ2_K11.7 GBQ2_K64details
Arete 27B27BQ3_K_M13.6 GBQ2_K51details
MiniMax H3 Image PE27BQ2_K11.3 GBQ2_K63details
Trinity Mini26B (2.0B act.)Q3_K_M12.3 GBQ3_K_M738details
GLiDE 27B26BQ3_K_M13.2 GBQ2_K53details
DiffusionGemma 26B A4B IT26B (4.0B act.)Q3_K_M13.2 GBQ2_K344details
Gemma 4 26B A4B IT26B (4.0B act.)Q3_K_M13.5 GBQ2_K333details
LFM2.5 24B A2B24B (2.0B act.)Q3_K_M11.7 GBQ3_K_M687details
ERNIE 4.5 21B A3B PT22BQ4_K_M13.6 GBQ3_K_M50details
ERNIE 4.5 21B A3B Thinking22BQ4_K_M13.6 GBQ3_K_M50details
gpt-oss Safeguard 20B22B (4.8B act.)Q8_012.3 GBQ8_0249details
gpt-oss 20B21B (4.2B act.)Q8_012.3 GBQ8_0277details
Kimi VL A3B Thinking 250616B (3.0B act.)Q6_K13.5 GBQ5_K_M273details
Kimi VL A3B Thinking16B (3.0B act.)Q6_K13.5 GBQ5_K_M273details
Kimi VL A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M305details
DeepSeek MoE 16B Base16B (2.8B act.)Q4_K_M12.5 GBQ2_K359details
LLaDA2.1 Mini16B (1.4B act.)Q6_K13.4 GBQ5_K_M572details
Moonlight 16B A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M297details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M335details
DeepSeek V2 Lite16B (2.7B act.)Q6_K12.8 GBQ6_K308details
DeepSeek V2 Lite Chat16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M335details
Qwen2.5 Coder 14B Instruct15BQ6_K13.5 GBQ3_K_M55details
DeepSeek R1 Distill Qwen 14B15BQ6_K13.5 GBQ3_K_M55details
Qwen3 14B15BQ6_K13.2 GBQ3_K_M55details
Phi 415BQ6_K13.4 GBQ2_K56details
Gemma 3 12B IT12BQ8_013.4 GBQ6_K54details
Llama Guard 4 12B12BQ6_K11.5 GBQ4_K_M68details
KORMo Web 11B11BQ8_013.0 GBQ5_K_M57details
Llama 3.2 11B Vision Instruct11BQ8_011.6 GBQ5_K_M65details
Llama 3.2 11B Vision11BQ8_012.4 GBQ5_K_M59details
GLM 4.6V Flash10BQ8_010.3 GBQ8_067details
GLM 4.1V 9B Thinking10BQ8_010.3 GBQ8_067details
Step3 VL 10B10BQ8_09.9 GBQ8_077details
SenseNova Loop 9B Preview9.7BQ8_010.0 GBQ8_070details
Qwen3.5 9B9.7BQ8_010.3 GBQ8_069details
Ornith 1.5 9B9.7BQ8_010.0 GBQ8_070details
SenseNova Loop 9B9.4BQ8_010.0 GBQ8_070details
MiMo V2.6 Distill Qwen 9B9.4BQ8_010.0 GBQ8_070details
GLM 4 9B9.4BQ8_010.3 GBQ8_067details
Apertus v1.5 8B8.9BQ8_010.5 GBQ8_071details
InternLM3 8B Instruct8.8BQ8_09.7 GBQ8_072details
Granite 4.2 8B8.8BQ8_010.5 GBQ6_K72details
Granite 4.1 8B8.8BQ8_010.5 GBQ6_K72details
Granite 4.1 8B Llmon Preview8.8BQ8_010.5 GBQ6_K72details
Qwen3 VL 8B Instruct8.8BQ8_09.9 GBQ8_077details
Molmo2 8B8.7BQ8_09.9 GBQ8_077details
LFM2.5 8B A1B8.5B (1.0B act.)Q8_09.1 GBQ8_0632details
Qwen2.5 VL 7B Instruct8.3BQ8_08.7 GBQ8_083details
UI TARS 1.5 7B8.3BQ8_08.7 GBQ8_083details
olmOCR 2 7B 10258.3BQ8_08.7 GBQ8_083details
olmOCR 7B 0225 Preview8.3BQ8_08.7 GBQ8_083details
UI TARS 7B DPO8.3BQ8_08.7 GBQ8_083details
Qwen3 8B8.2BQ8_09.9 GBQ8_077details
DeepSeek R1 0528 Qwen3 8B8.2BQ8_09.9 GBQ8_077details
Granite 3.3 8B Instruct8.2BQ8_09.8 GBQ8_077details
Granite 3.1 8B Instruct8.2BQ8_09.8 GBQ8_077details
Granite 3.2 8B Instruct8.2BQ8_09.8 GBQ8_077details
Apertus 8B Instruct 25098.1BQ8_09.6 GBQ8_078details
Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_079details
Llama 3.1 8B8.0BQ8_09.6 GBQ8_079details
Hermes 3 Llama 3.1 8B8.0BQ8_09.6 GBQ8_079details
Llama Guard 3 8B8.0BQ8_09.6 GBQ8_079details
DeepSeek R1 Distill Llama 8B8.0BQ8_09.6 GBQ8_079details
Meta Llama 3 8B Instruct8.0BQ8_09.6 GBQ8_079details
Meta Llama Guard 2 8B8.0BQ8_09.6 GBQ8_079details
Meta Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_079details
Aya Expanse 8B8.0BQ8_09.8 GBQ8_079details
Ling 3.0 Tiny7.9B (1.4B act.)Q8_08.7 GBQ8_0456details
MiMo 7B RL7.8BQ8_09.4 GBQ8_083details
InternLM2.5 7B Chat7.7BQ8_09.2 GBQ8_082details
InternLM2 Chat 7B7.7BQ8_09.2 GBQ8_082details
Qwen2.5 7B Instruct7.6BQ8_08.7 GBQ8_083details
DeepSeek R1 Distill Qwen 7B7.6BQ8_08.7 GBQ8_083details
Qwen2.5 Coder 7B Instruct7.6BQ8_08.7 GBQ8_083details
Olmo 3 7B Instruct7.3BQ8_010.3 GBQ8_087details
Olmo 3 1025 7B7.3BQ8_010.3 GBQ8_087details
Olmo 3 7B Think7.3BQ8_010.3 GBQ8_087details
Mistral 7B v0.17.2BQ8_08.6 GBQ8_087details
Mistral 7B Instruct v0.27.2BQ8_08.6 GBQ8_087details
Mistral 7B Instruct v0.17.2BQ8_08.6 GBQ8_087details
Falcon 7B7.2BQ8_07.7 GBQ8_088details
Falcon 7B Instruct7.2BQ8_07.4 GBQ8_091details
Granite 4.0 H Tiny6.9B (1.5B act.)F1613.6 GBQ8_0229details
OLMoE 1B 7B 09246.9B (1.3B act.)Q8_08.4 GBQ8_0493details
DeepSeek Coder 7B Instruct v1.56.9BQ8_011.2 GBno92details
DeepSeek Coder 6.7B Instruct6.7BQ8_011.1 GBno94details
DeepSeek Coder 6.7B Base6.7BQ8_011.1 GBno94details
Llama 2 7B HF6.7BQ8_011.1 GBno94details
Yi 6B 200K6.1BF1612.3 GBQ8_055details
Yi 6B6.1BF1612.3 GBQ8_055details
Molmo2 4B4.9BF1610.0 GBF1676details
WeVisOne VL 4B4.8BF1610.0 GBF1676details
Mage VL Cowork4.7BF1610.0 GBF1676details
Qianfan OCR4.7BF1610.1 GBF1676details
Qwen3.5 4B4.7BF169.2 GBF1678details
SingVL S1 4B4.5BF169.0 GBF1680details
LightOnOCR 3 4B4.5BF169.0 GBF1680details
Intern Decision 4B4.5BF169.0 GBF1680details
Qwen3 VL 4B Instruct4.4BF169.3 GBF1683details
Gemma 3 4B IT4.3BF168.4 GBF1687details
MedGemma 1.5 4B IT4.3BF168.4 GBF1687details
MedGemma 4B IT4.3BF168.4 GBF1687details
TranslateGemma 4B IT4.3BF169.2 GBF1678details
Gemma 3 4B PT4.3BF168.4 GBF1687details
Phi 3.5 Vision Instruct4.1BF1611.2 GBQ4_K_M81details
Qwen3 4B4.0BF169.3 GBF1684details
Qwen3 4B Instruct 25074.0BF169.3 GBF1683details
Granite Vision 4.1 4B4.0BF167.6 GBF1699details
Phi 4 Mini Instruct3.8BF168.9 GBF1688details
Phi 3 Mini 4K Instruct3.8BF1610.6 GBQ5_K_M88details
Phi 3.5 Mini Instruct3.8BF1610.6 GBQ5_K_M88details
Phi 3 Mini 128K Instruct3.8BF1610.6 GBQ5_K_M88details
Qwen2.5 VL 3B Instruct3.8BF168.0 GBF1689details
Granite 4.2 3B3.7BF168.0 GBF1692details
Granite 4.1 3B Llmon Preview3.7BF168.0 GBF1692details
Raon 1 Nano3.5BF167.0 GBF16107details
Granite 4.1 3B3.4BF167.6 GBF1699details
Granite 4.0 Micro3.4BF167.6 GBF1699details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16325details
DeepSeek VL2 Tiny3.4B (1.2B act.)F167.4 GBF16286details
Tiny Aya Global3.3BF167.5 GBF16100details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16332details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16334details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16334details
Granite 3.1 3B A800M Instruct3.3B (883M act.)F167.1 GBF16380details
Llama 3.2 3B Instruct3.2BF167.5 GBF16104details
Llama 3.2 3B3.2BF167.5 GBF16105details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF16104details
d1 3B3.1BF165.8 GBF16124details
LFM2.5 VL 3B3.1BF165.8 GBF16124details
Qwen2.5 3B Instruct3.1BF166.7 GBF16109details
SmolLM3 3B3.1BF166.9 GBF16109details
SmolLM3 3B Base3.1BF166.9 GBF16109details
Phi 22.8BF168.2 GBQ8_0121details
LFM2.5 2.6B2.7BF1610.8 GBF1662details
Granite 3.3 2B Instruct2.5BF165.8 GBF16133details
MiniCPM5 2B2.5BF165.7 GBF16133details
WeVisOne VL 2B2.4BF165.4 GBF16165details
Cosmos Reason2 2B2.4BF165.4 GBF16165details
Qwen3.5 2B2.3BF164.6 GBF16172details
SmolVLM Instruct2.2BF165.4 GBF16185details
Qwen3 1.7B2.0BF165.4 GBF16165details
d1 2B1.9BF164.0 GBF16194details
LFM3 VL 2B1.9BF164.0 GBF16194details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF16189details
LFM3 1.7B1.7BF167.2 GBF1697details
LFM3 1.7B Base1.7BF164.0 GBF16194details
SmolLM2 1.7B Instruct1.7BF165.2 GBF16196details
SmolLM2 1.7B1.7BF165.2 GBF16196details
SmolLM 1.7B1.7BF165.2 GBF16196details
Granite 4.0 1B1.6BF164.3 GBF16206details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF16218details
OLMo 2 0425 1B1.5BF164.4 GBF16226details
DeepSeek Coder 1.3B Instruct1.3BF164.5 GBF16250details
Llama 3.2 1B1.2BF163.2 GBF16271details
Llama 3.2 1B Instruct1.2BF163.2 GBF16271details
LFM2.5 1.2B Instruct1.2BF165.0 GBF16143details
LFM2 1.2B1.2BF163.0 GBF16287details
HunyuanOCR1.1BF163.5 GBF16300details
PaddleOCR VL 1.6959MF162.5 GBF16351details
Qwen3.5 0.8B873MF162.4 GBF16431details
LightOnOCR 3 0.8B853MF162.4 GBF16443details
FastVLM 0.5B759MF162.2 GBF16443details
Qwen3 0.6B752MF163.0 GBF16445details
GOT OCR2.0716MF162.8 GBF16469details
Nemotron 3.5 Parse631MF161.9 GBF16514details
GOT OCR 2.0 HF561MF162.5 GBF16599details
SmolVLM2 500M Video Instruct507MF161.6 GBF16819details
SmolVLM 500M Instruct507MF161.6 GBF16819details
Qwen2.5 0.5B Instruct494MF161.7 GBF16680details
LFM2.5 VL 450M449MF161.3 GBF16945details
SmolLM2 360M Instruct362MF161.5 GBF16926details
SmolLM2 360M362MF161.5 GBF16926details
LFM2.5 350M354MF161.9 GBF16472details

Bigger models with CPU offload

These popular models don't fit in the RTX 4070 Ti Super's VRAM at 4-bit, but run with llama.cpp offload, keeping part of the model in system RAM. Speed range is DDR4-3200 to DDR5-6000 (estimate). Method.

ModelParamsOffload plan
GLM 5.3 Flash321B MoEOffload Q2_K, 128 GB RAM · ~7.3–14 tok/s
gpt-oss 120B117B MoEOffload Q4_K_M, 64 GB RAM · ~14–28 tok/s
DeepSeek V4 Flash 0731304B MoEOffload Q2_K, 128 GB RAM · ~8.1–15 tok/s
DeepSeek V4 Flash291B MoEOffload Q3_K_M, 128 GB RAM · ~7.2–14 tok/s
GLM 4.5 Air110B MoEOffload Q4_K_M, 64 GB RAM · ~5.6–11 tok/s
MiniMax M2.5229B MoEOffload Q4_K_M, 128 GB RAM · ~5.6–11 tok/s
Hy3299B MoEOffload Q3_K_M, 128 GB RAM · ~4.2–8.4 tok/s

Comparing cards? The RTX 4070 Ti Super (launch MSRP $799) is in best GPUs for local LLMs under $800. See also Mac vs PC.

Just too big at 4-bit

These need up to 35% more memory than the RTX 4070 Ti Super 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
DiffusionGemma 26B A4B IT17.1 GB1.9 GB
Gemma 4 26B A4B IT17.3 GB2.1 GB
Gemma 3 27B IT17.3 GB2.1 GB
Arete 27B17.4 GB2.2 GB
Qwen3.8 27B17.6 GB2.4 GB
Muse Glimmer 30B17.9 GB2.7 GB
Qwen3.5 27B18.1 GB2.9 GB
Qwen3.6 27B18.1 GB2.9 GB
GLM 4.7 Flash18.3 GB3.1 GB
Hy Memory 30B A3B18.5 GB3.3 GB
Qwen3 Coder 30B A3B Instruct18.8 GB3.6 GB
North Mini Code 1.018.8 GB3.6 GB

Questions

What is the biggest model that runs on the RTX 4070 Ti Super?

Of the models we track, the largest that fits at 8K context is Maxwell V1 Flash (37B) at Q2_K, needing about 14.0 GB.

How much of the RTX 4070 Ti Super'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.