Graphics cards
Which AI models run on the RTX 5070 Ti (16 GB)?
The RTX 5070 Ti (16 GB) has 16 GB of memory, about 15.0 GB of it usable for a model, and 896 GB/s of memory bandwidth. 51 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026 · Vendor specs
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Nemotron Nano 9B v29B | Q8_0 | 10.8 GB | ~52 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q8_0 | 12.0 GB | ~86 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~144 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~150 tok/s ModelFit est. |
| Qwen2.5 14B Instruct14B | Q4_K_M | 12.3 GB | ~78 tok/s ModelFit est. |
| Phi-3 Medium 14B14B | Q4_K_M | 12.3 GB | ~45 tok/s our est. |
| Phi-4 14B14B | Q4_K_M | 12.8 GB | ~77 tok/s ModelFit est. |
| Qwen2.5 Coder 14B14B | Q4_K_M | 12.3 GB | ~78 tok/s ModelFit est. |
| Qwen3 14B14B | Q4_K_M | 12.3 GB | ~77 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 14B14B | Q4_K_M | 12.3 GB | ~78 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~79 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~294 tok/s our est. |
| Mistral Nemo 12B12B | Q8_0 | 13.4 GB | ~58 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~91 tok/s ModelFit est. |
| Gemma 4 12B12B | Q8_0 | 14.1 GB | ~57 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q8_0 | 11.2 GB | ~77 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~98 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~133 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~129 tok/s ModelFit est. |
| Jebadiah 9B9B | Q8_0 | 11.0 GB | ~84 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~119 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~99 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~128 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~112 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~296 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~85 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~83 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~115 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~89 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~144 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~92 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~133 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~143 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~163 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~154 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~143 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~231 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~181 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~256 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~226 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~230 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~256 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~250 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~258 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~361 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~369 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~397 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~370 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~414 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~523 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~407 tok/s ModelFit est. |
Speeds come from ModelFit's estimates (CC BY 4.0) where it covers the model, otherwise from our bandwidth formula. Method
Fits only at 3-bit or lower
Too big for this machine
gpt-oss-20b (15.1 GB), LFM2 24B-A2B Instruct (15.3 GB), Mistral Small 3.1 (16.4 GB), Devstral Small 2 24B (16.6 GB), Gemma 4 26B-A4B (17.4 GB), Qwen3.5 27B Instruct (17.4 GB), Qwen3.8-27B (17.9 GB), Granite 4.2 30B (17.9 GB), Jebadiah 27B (18.2 GB), Muse Glimmer 30B (18.3 GB), Mistral Small 22B (18.4 GB), AREX-2 27B (18.6 GB) and more.
Questions
What is the best AI model for the RTX 5070 Ti (16 GB)?
Qwen3.5 9B Instruct at Q8_0: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 86 tok/s, ModelFit est.).
How much memory can a model use on the RTX 5070 Ti (16 GB)?
About 15.0 GB of the 16 GB.
How fast is the RTX 5070 Ti (16 GB) for local LLMs?
Decode speed is limited by memory bandwidth: 896 GB/s. A model that reads 10 GB per token runs at under 90 tokens per second.