Home / AI GPUs / NVIDIA RTX 5070 Ti 16 GB
NVIDIA · GeForce
NVIDIA RTX 5070 Ti 16 GB
16 GB GDDR7 advertised VRAM. Usable memory for calculations is 90% of advertised capacity. This page is the chip + VRAM entity — not a single cooler SKU.
Models that fit (calculated)
| Model | Params | Q4 | Q8 | FP16 | Max context in VRAM |
|---|---|---|---|---|---|
| Qwen2.5 0.5B Instruct | 494M | Fits | Fits | Fits | 32K |
| TinyLlama 1.1B Chat v1.0 | 1.1B | Fits | Fits | Fits | 2K |
| Llama 3.2 1B Instruct | 1.2B | Fits | Fits | Fits | 128K |
| Qwen2.5 1.5B Instruct | 1.5B | Fits | Fits | Fits | 32K |
| Qwen2.5-Coder 1.5B Instruct | 1.5B | Fits | Fits | Fits | 32K |
| SmolLM2 1.7B Instruct | 1.7B | Fits | Fits | Fits | 8K |
| Gemma 2 2B Instruct | 2.6B | Fits | Fits | Fits | 8K |
| Qwen2.5 3B Instruct | 3.1B | Fits | Fits | Fits | 32K |
| Llama 3.2 3B Instruct | 3.2B | Fits | Fits | Fits | 64K |
| Phi-3.5 Mini Instruct | 3.8B | Fits | Fits | Fits | 16K |
| Phi-3 Mini 128K Instruct | 3.8B | Fits | Fits | Fits | 16K |
| Phi-3 Mini 4K Instruct | 3.8B | Fits | Fits | Fits | 4K |
| Phi-4 Mini Instruct | 3.8B | Fits | Fits | Fits | 64K |
| Code Llama 7B Instruct | 6.7B | Fits | Fits | Offload | 16K |
| Vicuna 7B v1.5 | 6.7B | Fits | Fits | Offload | 4K |
| DeepSeek LLM 7B Chat | 6.9B | Fits | Fits | Offload | 4K |
| StarCoder2 7B | 7.2B | Fits | Fits | Offload | 16K |
| Falcon 7B Instruct | 7.2B | Fits | Fits | Offload | 16K |
| OpenChat 3.5 7B | 7.2B | Fits | Fits | Offload | 8K |
| Mistral 7B Instruct v0.3 | 7.3B | Fits | Fits | Offload | 32K |
| OLMo 2 7B Instruct | 7.3B | Fits | Fits | Offload | 4K |
| Falcon 3 7B Instruct | 7.5B | Fits | Fits | Offload | 32K |
| DeepSeek R1 Distill Qwen 7B | 7.6B | Fits | Fits | Offload | 128K |
| Qwen2.5 7B Instruct | 7.6B | Fits | Fits | Offload | 32K |
| Qwen2.5-Coder 7B Instruct | 7.6B | Fits | Fits | Offload | 32K |
| Qwen2.5-Math 7B Instruct | 7.6B | Fits | Fits | Offload | 4K |
| Qwen2 7B Instruct | 7.6B | Fits | Fits | Offload | 32K |
| DeepSeek R1 Distill Llama 8B | 8.0B | Fits | Fits | Offload | 64K |
| Hermes 3 Llama 3.1 8B | 8.0B | Fits | Fits | Offload | 64K |
| Llama 3.1 8B Instruct | 8.0B | Fits | Fits | Offload | 64K |
| Llama 3 8B Instruct | 8.0B | Fits | Fits | Offload | 8K |
| Qwen3 8B | 8.2B | Fits | Fits | Offload | 40K |
| Yi 1.5 9B Chat | 8.8B | Fits | Fits | Offload | 4K |
| Gemma 2 9B Instruct | 9.2B | Fits | Fits | Offload | 8K |
| GLM-4-9B-0414 | 9.4B | Fits | Fits | Offload | 32K |
| GLM-4 9B Chat | 9.4B | Fits | Fits | Offload | 8K |
| Falcon 3 10B Instruct | 10B | Fits | Fits | Offload | 32K |
| SOLAR 10.7B Instruct | 11B | Fits | Fits | Offload | 4K |
| Mistral Nemo 12B Instruct | 12B | Fits | Offload | Offload | 32K |
| Code Llama 13B Instruct | 13B | Fits | Offload | Offload | 8K |
| Vicuna 13B v1.5 | 13B | Fits | Offload | Offload | 4K |
| OLMo 2 13B Instruct | 14B | Fits | Offload | Offload | 4K |
| Phi-3 Medium 128K Instruct | 14B | Fits | Offload | Offload | 32K |
| Phi-3 Medium 4K Instruct | 14B | Fits | Offload | Offload | 4K |
| DeepSeek R1 Distill Qwen 14B | 15B | Fits | Offload | Offload | 32K |
| Phi-4 | 15B | Fits | Offload | Offload | 16K |
| Qwen2.5 14B Instruct | 15B | Fits | Offload | Offload | 32K |
| Qwen3 14B | 15B | Fits | Offload | Offload | 32K |
| StarCoder2 15B | 16B | Fits | Offload | Offload | 16K |
| GPT-OSS 20B | 22B | Offload | Offload | No | 32K |
| Mistral Small 24B Instruct | 24B | Offload | Offload | No | 8K |
| Gemma 2 27B Instruct | 27B | Offload | Offload | No | — |
| DeepSeek R1 Distill Qwen 32B | 33B | Offload | Offload | No | — |
| Qwen2.5 32B Instruct | 33B | Offload | Offload | No | — |
| Qwen2.5-Coder 32B Instruct | 33B | Offload | Offload | No | — |
| QwQ 32B | 33B | Offload | Offload | No | — |
| Qwen3 32B | 33B | Offload | Offload | No | — |
| Code Llama 34B Instruct | 34B | Offload | No | No | — |
| Yi 1.5 34B Chat | 34B | Offload | No | No | — |
| Mixtral 8x7B Instruct | 47B | Offload | No | No | — |
| DeepSeek R1 Distill Llama 70B | 71B | No | No | No | — |
| Hermes 3 Llama 3.1 70B | 71B | No | No | No | — |
| Llama 3.1 70B Instruct | 71B | No | No | No | — |
| Llama 3.3 70B Instruct | 71B | No | No | No | — |
| Qwen2.5 72B Instruct | 73B | No | No | No | — |
| GPT-OSS 120B | 117B | No | No | No | — |
| Mixtral 8x22B Instruct | 141B | No | No | No | — |
Available graphics cards
These are Icecat product SKUs mapped to this chip. Different board-partner cards are not assumed to share a price. Amazon CTAs appear only for EXACT/HIGH matches that are not bundled accessories.
ASUS
ASUS TUF Gaming TUF-RTX5070TI-O16G-GAMING NVIDIA GeForce RTX 5070 Ti 16 GB GDDR7
16 GB · Amazon EXACT
$1099.99
Check price on Amazon
MSI
MSI GeForce RTX 5070 Ti 16G VENTUS 3X OC NVIDIA 16 GB GDDR7
16 GB · Amazon EXACT
$1179.99
Check price on Amazon
GIGABYTE
GIGABYTE GeForce RTX 5070 Ti GAMING OC 16G Graphics Card
16 GB · Amazon EXACT
$1088.24
Check price on Amazon
MSI
MSI GAMING GeForce RTX 5070 Ti 16G TRIO OC NVIDIA 16 GB GDDR7
16 GB · Amazon EXACT
$999.00
Check price on Amazon
ASUS
ASUS Prime -RTX5070TI-O16G NVIDIA GeForce RTX 5070 Ti 16 GB GDDR7
16 GB · Amazon EXACT
Check price on Amazon
GIGABYTE
GIGABYTE GeForce RTX 5070 Ti WINDFORCE OC SFF 16G Graphics Card
16 GB · Amazon EXACT
Check price on AmazonASUS
ASUS Prime -RTX5070TI-16G NVIDIA GeForce RTX 5070 Ti 16 GB GDDR7
16 GB · Amazon EXACT
Check price on Amazon
ASUS
ASUS ROG -STRIX-RTX5070TI-O16G-GAMING NVIDIA GeForce RTX 5070 Ti 16 GB GDDR7
16 GB · Amazon unmatched
Check availability
Sources
GPU identity and VRAM: Icecat structured specifications. Compatibility: RigForAI calculated estimate. Amazon: live affiliate match on individual SKUs, via /go/amazon/.