GeForce RTX 5070
NVIDIA GeForce RTX 5070: 12 GB of memory at 672 GB/s. Below: the open models it can run, estimated at 12 GB with an 8K context. Fast GDDR7 (672 GB/s) but only 12 GB, so it holds smaller models than the cheaper 16 GB RTX 5060 Ti; best suited to 8–14B models.
Last updated: 2026-10-14
Specifications
What it can run
Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.
| Model | Params | Best quant | Memory | tok/s (est.) |
|---|---|---|---|---|
| Phi-4 (14B) | 14B | Q5_K_M | 11.8 GiB | 47 |
| Gemma 3 12B IT | 12B | Q6_K | 11.0 GiB | 48 |
| Gemma 4 12B Unified IT | 11.95B | Q6_K | 10.5 GiB | 48 |
| Qwen3.5-9B | 9B | Q8_0 | 10.1 GiB | 49 |
| Qwen3-8B | 8.2B | Q8_0 | 10.1 GiB | 54 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | Q8_0 | 10.1 GiB | 54 |
| Llama 3.1 8B Instruct | 8B | Q8_0 | 9.8 GiB | 55 |
| Gemma 4 E4B IT | 8B | Q8_0 | 9.1 GiB | 55 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 73 |
| Kimi K2.6 | 1000B (32B) | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B (37B) | Doesn't fit | – | – |
| DeepSeek-V4-Flash | 284B (13B) | Doesn't fit | – | – |
| Qwen3.8-Flash-Next | 180B (6B) | Doesn't fit | – | – |
| Qwen3.5-122B-A10B | 122B (10B) | Doesn't fit | – | – |
| Mistral Small 4 119B (2603) | 119B (6.5B) | Doesn't fit | – | – |
| gpt-oss-120b | 117B (5.1B) | Doesn't fit | – | – |
| Llama 4 Scout 17B-16E Instruct | 109B (17B) | Doesn't fit | – | – |
| GLM-4.5-Air | 106B (12B) | Doesn't fit | – | – |
| Qwen3-Coder-Next (80B-A3B) | 80B (3B) | Doesn't fit | – | – |
| Llama 3.3 70B Instruct | 70B | Doesn't fit | – | – |
| Qwen3.5-35B-A3B | 35B (3B) | Doesn't fit | – | – |
| Qwen3.6-35B-A3B | 35B (3B) | Doesn't fit | – | – |
| Qwen3-32B | 32.8B | Doesn't fit | – | – |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | Doesn't fit | – | – |
| Gemma 4 31B IT | 30.7B | Doesn't fit | – | – |
| Qwen3-30B-A3B (2507) | 30.5B (3.3B) | Doesn't fit | – | – |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B (3.3B) | Doesn't fit | – | – |
| GLM-4.7-Flash (30B-A3B) | 30B (3B) | Doesn't fit | – | – |
| Qwen3.5-27B | 27B | Doesn't fit | – | – |
| Qwen3.6-27B | 27B | Doesn't fit | – | – |
| Qwen3.8-27B | 27B | Doesn't fit | – | – |
| Gemma 3 27B IT | 27B | Doesn't fit | – | – |
| Gemma 4 26B A4B IT | 25.2B (3.8B) | Doesn't fit | – | – |
| Mistral Small 3.2 24B Instruct (2506) | 24B | Doesn't fit | – | – |
| Magistral Small 1.2 (2509) | 24B | Doesn't fit | – | – |
| Devstral Small 2 24B Instruct (2512) | 24B | Doesn't fit | – | – |
| gpt-oss-20b | 21B (3.6B) | Doesn't fit | – | – |
Prices
Latest price at each shop, as listed on the day we checked.
| Region | Shop | Listing | Price | Per GB | Checked |
|---|---|---|---|---|---|
| Taiwan | 原價屋 CoolPC | ｛INNO3D RTX5070 TWIN X2｝2512MHz/25cm/雙風扇/註四年Line on the shop's public price list (no per-product page); list stamped 2026/10/14 15:47 | NT$28,888 | NT$2,407/GB | 2026-10-14 |
| Taiwan | momo購物網 | 【MSI 微星】GeForce RTX 5070 12G SHADOW 2X OC 顯示卡 | NT$29,990 | NT$2,499/GB | 2026-10-14 |
| US | Newegg | ZOTAC GAMING GeForce RTX 5070 SOLID OC 12GB GDDR7 ZT-B50700J-10A | US$829.99 | US$69/GB | 2026-10-14 |
- Taiwan value: about 97.0 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 3.4 tok/s per NT$1,000.
- US value: about 97.0 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 11.7 tok/s per US$100.
A price history chart appears once we have checked this device on two or more days.
All prices →Frequently asked questions
Which LLMs can the GeForce RTX 5070 run?
With 12 GB and an 8K context, the largest models that fit include: Phi-4 (14B), Gemma 3 12B IT, Gemma 4 12B Unified IT, Qwen3.5-9B, Qwen3-8B. See the full table below.
How fast is the GeForce RTX 5070 for local LLMs?
Generation speed is mostly set by memory bandwidth (672 GB/s). For Llama 3.1 8B Instruct at Q8_0, expect roughly 55 tokens/s; bigger models are slower.
Can the GeForce RTX 5070 run 70B models?
Llama 3.3 70B Instruct does not fit on the GeForce RTX 5070 (12 GB), even at Q4_K_M with an 8K context.
Sources
- https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5070-family/
- https://www.nvidia.com/en-us/geforce/graphics-cards/compare/
- https://www.nvidia.com/en-us/geforce/news/rtx-5070-out-now/
- https://nvidianews.nvidia.com/news/nvidia-blackwell-geforce-rtx-50-series-opens-new-world-of-ai-computer-graphics
- https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units