Intern-S2-Preview-397B GPU Requirements: VRAM & Cheapest GPU
Intern-S2-Preview-397B has about 403B parameters. See exactly how much GPU memory it needs at FP16, INT8, and INT4, and the cheapest GPU to run it, with live hourly pricing from 5+ data center partners.
To run Intern-S2-Preview-397B for inference at FP16, you need roughly 879 GB of VRAM. The cheapest fit on Spheron is 4x B300 288GB at about $23.24/hr. Quantize to INT4 to run it on a smaller, cheaper GPU.
Estimated peak VRAM including weights, activations, and KV cache. Add 10% headroom for production traffic.
- 01$5.81/hr$23.24/hr4× B300 288GBCHEAPESTBlackwell Ultra · HBM3e
- 02$3.31/hr$26.48/hr8× H200 141GBHopper · HBM3e
- 03$5.34/hr$42.72/hr8× B200 192GBBlackwell · HBM3e
Live pricing aggregated from 5+ data center partners. Per-minute billing, no commitments.
VRAM required to run Intern-S2-Preview-397B
Estimated peak VRAM at context length 4,096 and batch size 1, including weights, activations, and KV cache. Quantizing to INT8 (Q8) or INT4 (Q4) cuts memory roughly in half and in quarter.
| Precision | Inference | LoRA fine-tune | Full fine-tune |
|---|---|---|---|
| FP16 | 879 GB | 1319 GB | 3518 GB |
| INT8 | 440 GB | 660 GB | 1759 GB |
| INT4 | 220 GB | 330 GB | 879 GB |
Cheapest GPU to run Intern-S2-Preview-397B by precision
Full precision. Best quality, highest memory.
8-bit quantized. ~2x smaller, minimal quality loss.
4-bit quantized. ~4x smaller, runs on smaller GPUs.
Inference vs fine-tuning Intern-S2-Preview-397B
Inference only holds the model weights plus a KV cache, so it is the cheapest setup. LoRA fine-tuning adds a small adapter and roughly 50% more memory. Full fine-tuning holds gradients and optimizer state on top of the weights, which is about 4x the inference footprint, so it often needs multiple GPUs even when inference fits on one. For Intern-S2-Preview-397B, an on-demand B300 288GB instance covers inference and LoRA, while a full fine-tune needs several times that memory and often spans multiple GPUs. Check the live GPU pricing for current rates.
Similar models
Compare GPU requirements for models in the same class.
Intern-S2-Preview-397B GPU questions
Intern-S2-Preview-397B has about 403B parameters. At FP16 it needs roughly 879 GB of VRAM for inference, including weights, activations, and KV cache. Quantized to INT4 that drops to around 220 GB. Leave about 10% headroom for production traffic.
For FP16 inference, the cheapest fit on Spheron is 4x B300 288GB at about $23.24/hr. If you quantize to INT4, 4x A100 80GB at about $4.80/hr runs it for less. Pricing is aggregated live from 5+ data center partners with per-minute billing.
LoRA fine-tuning adds roughly 50% on top of inference memory, so it usually fits the same class of GPU. Full fine-tuning holds gradients and optimizer state and needs about 4x the inference VRAM, which often means multiple GPUs for Intern-S2-Preview-397B. The VRAM matrix above shows the exact estimate for each setup.
We read the parameter count directly from the model's safetensors metadata on HuggingFace, then estimate peak VRAM from weights, activations, KV cache, and framework overhead at your chosen precision. The estimate lands within about 15% of real-world use for most transformer models.
Quantized to INT4, Intern-S2-Preview-397B needs about 220 GB of VRAM, so it is too large for a single 24 GB RTX 4090 and needs a bigger card or multiple GPUs. At FP16 it needs roughly 879 GB, which usually means a data center GPU. The precision picks above list the cheapest GPU that fits each setup.