RTX 4070S
The RTX 4070S is a cloud GPU with 12 GB of memory and 220 W TDP. It is currently available from 1 provider starting at $0.09/hr, with a market median of $0.09/hr across 1 offering.
Best deal
Hardware specifications
- Architecture
- Ada Lovelace
- VRAM
- 12 GB
- Memory type
- GDDR6X
- Memory bandwidth
- 504 GB/s
- FP32
- 36 TFLOPS
- TDP
- 220 W
Same across all providers.
Market comparison
All-time price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | 24 GB | HK | $0.09/hr | — | $0.09/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 8× |
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Barely fits on 8× | Barely fits on 5× |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | Needs >8 GPUs | Barely fits on 5× | Barely fits on 3× |
Qwen3 32B Alibaba | 32.8B | Barely fits on 8× | 5× · 14% spare | 3× · 6 GB free |
Qwen2.5 14B Alibaba | 14B | Barely fits on 3× | 2× · 4.7 GB free | Barely fits on 1× |
Llama 3.1 8B Meta | 8B | Barely fits on 2× | Barely fits on 1× | 1× · 5.3 GB free |
Mistral 7B Mistral AI | 7B | 2× · 5.8 GB free | 1× · 2 GB free | 1× · 6.1 GB free |
Qwen3 4B Alibaba | 4B | Barely fits on 1× | 1× · 5.6 GB free | 1× · 8.3 GB free |
Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.
Similar GPUs
See more GPUs like this in
Frequently asked questions
How much does the RTX 4070S cost per hour?
The cheapest RTX 4070S offering starts at $0.09/hr, and the market median is $0.09/hr.
Which cloud providers offer the RTX 4070S?
We track RTX 4070S offerings from HardwareHQ.
How much VRAM does the RTX 4070S have?
The RTX 4070S has 12 GB of VRAM.
What LLMs can run on the RTX 4070S?
With 12 GB of VRAM, the RTX 4070S can run 8 of our tracked models in 4-bit quantization, including gpt-oss-120b, Qwen3.6 35B-A3B, Qwen3 32B. 5 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple RTX 4070Ss?
With 8× RTX 4070S (96 GB total), the largest tracked model that fits in 16-bit is Mistral 7B (7B params), which needs 2× GPUs.
Where is the RTX 4070S cheapest?
The cheapest RTX 4070S offering in our catalog is HardwareHQ at $0.09/hr per GPU-hour (×1).