What LLMs Can the RTX 5070 Ti 16GB Run?
The RTX 5070 Ti 16GB has 16 GB of VRAM and 896 GB/s of bandwidth. It runs 28 of 58 models fully at Q4_K_M with 8K context, up to Gemma 4 26B-A4B, and generates about 104 tokens/s on an 8B model.
28 of 58 models fit
RTX 5070 Ti 16GB (16.0 GB) at Q4_K_M with 8K context. Largest that fits fully: Gemma 4 26B-A4B.
| Model | Needs | Status | Speed | Best quant that fits |
|---|---|---|---|---|
| gpt-oss-20b | 12.9 GB | Fits | ~158 tok/s | MXFP4 (official) |
| Qwen 2.5 14B | 10.7 GB | Fits | ~58 tok/s | Q6_K |
| DeepSeek R1 Distill Qwen 14B | 10.7 GB | Fits | ~58 tok/s | Q6_K |
| Phi-4 14B | 10.6 GB | Fits | ~58 tok/s | Q6_K |
| Qwen 3 14B | 10.5 GB | Fits | ~59 tok/s | Q6_K |
| Ministral 3 14B | 9.7 GB | Fits | ~64 tok/s | Q6_K |
| Mistral Nemo 12B | 9.0 GB | Fits | ~70 tok/s | Q8_0 |
| Gemma 3 12B | 8.8 GB | Fits | ~70 tok/s | Q8_0 |
| Ministral 3 8B | 6.7 GB | Fits | ~98 tok/s | Q8_0 |
| Qwen 3 8B | 6.6 GB | Fits | ~101 tok/s | Q8_0 |
| Qwen 3.5 9B | 6.4 GB | Fits | ~100 tok/s | Q8_0 |
| Llama 3.1 8B | 6.3 GB | Fits | ~104 tok/s | Q8_0 |
| DeepSeek R1 Distill Llama 8B | 6.3 GB | Fits | ~104 tok/s | Q8_0 |
| Mistral 7B v0.3 | 5.7 GB | Fits | ~114 tok/s | Q8_0 |
| Gemma 4 E4B | 5.7 GB | Fits | ~112 tok/s | Q8_0 |
| Qwen 2.5 7B | 5.6 GB | Fits | ~116 tok/s | Q8_0 |
| DeepSeek R1 Distill Qwen 7B | 5.6 GB | Fits | ~116 tok/s | Q8_0 |
| Qwen 3 4B | 4.2 GB | Fits | ~179 tok/s | FP16 / BF16 |
| Phi-4 Mini | 4.1 GB | Fits | ~191 tok/s | FP16 / BF16 |
| Gemma 4 E2B | 4.0 GB | Fits | ~175 tok/s | FP16 / BF16 |
| Gemma 3 4B | 3.7 GB | Fits | ~193 tok/s | FP16 / BF16 |
| Qwen 3.5 4B | 3.7 GB | Fits | ~199 tok/s | FP16 / BF16 |
| Ministral 3 3B | 3.5 GB | Fits | ~218 tok/s | FP16 / BF16 |
| Llama 3.2 3B | 3.5 GB | Fits | ~226 tok/s | FP16 / BF16 |
| Llama 3.2 1B | 1.7 GB | Fits | ~595 tok/s | FP16 / BF16 |
| Gemma 3 1B | 1.6 GB | Fits | ~741 tok/s | FP16 / BF16 |
| Mistral Small 3.1 24B | 15.6 GB | Tight fit | ~38 tok/s | IQ4_XS |
| Gemma 4 26B-A4B | 15.6 GB | Tight fit | ~134 tok/s | IQ4_XS |
| Qwen3-Next 80B-A3B | 46.3 GB | 33% on GPU | ~26 tok/s | – |
| Qwen 2.5 72B | 44.5 GB | 34% on GPU | ~1.3 tok/s | – |
| Llama 3.3 70B | 43.2 GB | 35% on GPU | ~1.4 tok/s | – |
| DeepSeek R1 Distill Llama 70B | 43.2 GB | 35% on GPU | ~1.4 tok/s | – |
| Mixtral 8x7B | 28.0 GB | 54% on GPU | ~9.7 tok/s | – |
| Qwen 2.5 32B | 21.4 GB | 70% on GPU | ~5.7 tok/s | Q2_K |
| Qwen 2.5 Coder 32B | 21.4 GB | 70% on GPU | ~5.7 tok/s | Q2_K |
| DeepSeek R1 Distill Qwen 32B | 21.4 GB | 70% on GPU | ~5.7 tok/s | Q2_K |
| Qwen 3 32B | 21.4 GB | 70% on GPU | ~5.7 tok/s | Q2_K |
| Qwen 3.5 35B-A3B | 21.0 GB | 72% on GPU | ~51 tok/s | Q2_K |
| Qwen 3.6 35B-A3B | 21.0 GB | 72% on GPU | ~51 tok/s | Q2_K |
| Gemma 4 31B | 19.8 GB | 76% on GPU | ~7.1 tok/s | Q2_K |
| Qwen 3 30B-A3B | 18.8 GB | 80% on GPU | ~51 tok/s | Q2_K |
| Qwen3-Coder 30B-A3B | 18.8 GB | 80% on GPU | ~51 tok/s | Q2_K |
| Gemma 3 27B | 17.6 GB | 86% on GPU | ~12 tok/s | Q3_K_M |
| Qwen 3.5 27B | 16.9 GB | 89% on GPU | ~14 tok/s | IQ4_XS |
| Qwen 3.6 27B | 16.9 GB | 89% on GPU | ~14 tok/s | IQ4_XS |
| Qwen 3.8 27B | 16.9 GB | 89% on GPU | ~14 tok/s | IQ4_XS |
| Kimi K2.6 | 566 GB | Too small | – | – |
| DeepSeek R1 671B | 380 GB | Too small | – | – |
| Llama 3.1 405B | 234 GB | Too small | – | – |
| Qwen 3.5 397B-A17B | 226 GB | Too small | – | – |
| DeepSeek V4 Flash | 161 GB | Too small | – | – |
| Qwen 3 235B-A22B | 135 GB | Too small | – | – |
| MiniMax-M2 | 133 GB | Too small | – | – |
| Qwen 3.5 122B-A10B | 70.2 GB | Too small | – | – |
| Mistral Small 4 119B | 68.2 GB | Too small | – | – |
| gpt-oss-120b | 67.2 GB | Too small | – | – |
| Llama 4 Scout | 64.0 GB | Too small | – | – |
| GLM-4.5-Air | 62.1 GB | Too small | – | – |
RTX 5070 Ti 16GB for local AI
Nearly RTX 3090-class bandwidth with 16 GB and modern features. It is fast for anything up to about 24B at Q4_K_M.
Setup tips: fast for 14–20B models and mixture-of-experts models up to about 16 GB. Use a recent llama.cpp or Ollama build compiled for Blackwell. For 27B+ models, a Q3 quant or partial offload works but loses some quality or speed.
Among the 14 devices we track with about 16 GB of usable memory, the RTX 5070 Ti 16GB ranks 2 of 14 for text-generation speed, because generation speed follows memory bandwidth. Others in the same class: RTX 5080 16GB, RTX 4080 Super 16GB, RTX 4080 16GB, RTX 4070 Ti Super 16GB. They all hold the same models; the faster ones simply answer sooner.
Our picks for the RTX 5070 Ti 16GB
The model we would run first for each job, chosen from our recommendations by what fits fully with an 8K context. "Best quant" is the highest quality that fits; "max context" is at Q4_K_M or the native format.
| Task | Model | Best quant | Max context | Speed |
|---|---|---|---|---|
| Best all-rounder | Qwen 3 14B | Q6_K | 37K | ~59 tok/s |
| Coding | gpt-oss-20b | MXFP4 (official) | 55K | ~151 tok/s |
| Fastest replies | gpt-oss-20b | MXFP4 (official) | 55K | ~151 tok/s |
| Long documents (64K+) | Qwen 3.5 9B | Q8_0 | 256K | ~100 tok/s |
| Images in, text out | Ministral 3 14B | Q6_K | 42K | ~64 tok/s |
| Image generation | Qwen-Image | GGUF Q5_K_S | – | – |
| Spec | Value |
|---|---|
| Memory | 16 GB |
| Memory bandwidth | 896 GB/s |
| Architecture | Blackwell |
| Released | 2025-02 |
| Llama 3.1 8B Q4_K_M speed | ~104 tok/s |
| Largest model that fits | Gemma 4 26B-A4B |
Image and video models on the RTX 5070 Ti 16GB
Peak VRAM with model swapping (ComfyUI default on smaller cards).
| Model | FP8 | FP8 fit | GGUF Q4 | Q4 fit |
|---|---|---|---|---|
| Stable Diffusion 1.5 | 1.8 GB | Fits | 1.7 GB | Fits |
| SDXL 1.0 | 4.1 GB | Fits | 4.1 GB | Fits |
| Stable Diffusion 3.5 Medium | 6.4 GB | Fits | 6.4 GB | Fits |
| Stable Diffusion 3.5 Large | 8.6 GB | Fits | 6.4 GB | Fits |
| FLUX.1 [dev] | 12.1 GB | Fits | 7.3 GB | Fits |
| FLUX.1 [schnell] | 12.1 GB | Fits | 7.3 GB | Fits |
| Qwen-Image | 20.4 GB | 74% on GPU | 12.3 GB | Fits |
| Wan 2.2 A14B (T2V / I2V) | 18.8 GB | 80% on GPU | 13.2 GB | Fits |
| Wan 2.2 TI2V 5B | 8.0 GB | Fits | 6.5 GB | Fits |
| HunyuanVideo | 18.3 GB | 82% on GPU | 13.1 GB | Fits |
| FLUX.1 Kontext [dev] | 12.3 GB | Fits | 7.5 GB | Fits |
| FLUX.2 [dev] | 31.0 GB | 49% on GPU | 23.6 GB | 64% on GPU |
| Z-Image Turbo | 6.8 GB | Fits | 4.9 GB | Fits |
| Qwen-Image-Edit 2509 | 20.5 GB | 73% on GPU | 12.4 GB | Fits |
| LTX-2 | 19.2 GB | 78% on GPU | 12.6 GB | Fits |
Upgrade path
The next step up is the Radeon RX 7900 XT 20GB with 20 GB.
Comparisons
RTX 5070 Ti 16GB for LLMs: common questions
Can the RTX 5070 Ti 16GB run Llama 3.3 70B?
Only partly. It needs about 43.2 GB at Q4_K_M, so about 35% fits in VRAM and the rest runs from system RAM, which is slow.
Can the RTX 5070 Ti 16GB run Qwen 3 32B?
Only partly. It needs about 21.4 GB at Q4_K_M, so about 70% fits in VRAM and the rest runs from system RAM, which is slow. Q2_K fits fully.
Can the RTX 5070 Ti 16GB run Qwen 3 14B?
Yes. Qwen 3 14B needs about 10.5 GB at Q4_K_M with 8K context, and the best quality that fits is Q6_K.
How fast is the RTX 5070 Ti 16GB for LLMs?
About 104 tokens per second for an 8B model at Q4_K_M, based on its 896 GB/s memory bandwidth. Larger models scale down roughly in proportion to their size.