Intern S2 Preview 397B — Hardware Requirements & GPU Compatibility
Vision
Intern S2 Preview 397B is a 403.4B-parameter open language model from InternLM in the Intern-S2 family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 807.27 GB of VRAM — see which GPUs and Macs can run it below.
62 downloads
48 likesSpecifications
- Publisher
- InternLM
- Family
- Intern-S2
- Parameters
- 403.4B
- Architecture
- InternS2PreviewForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 251,392
- Release Date
- 2026-07-16
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Intern S2 Preview 397B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 807.3 GB | 823.3 GB | 806.85 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Intern S2 Preview 397B?
BF16 · 807.3 GBIntern S2 Preview 397B (BF16) requires 807.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1050+ GB is recommended. Using the full 262K context window can add up to 16.0 GB, bringing total usage to 823.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Related Models
Frequently Asked Questions
- How much VRAM does Intern S2 Preview 397B need?
Intern S2 Preview 397B requires 807.3 GB of VRAM at BF16. Full 262K context adds up to 16.0 GB (823.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 403.4B × 16 bits ÷ 8 = 806.8 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 16.5 GB (at full 262K context)
VRAM usage by quantization
BF16807.3 GBBF16 + full context823.3 GB- Can NVIDIA GeForce RTX 5090 run Intern S2 Preview 397B?
No — Intern S2 Preview 397B requires at least 807.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Intern S2 Preview 397B on a Mac?
Intern S2 Preview 397B requires at least 807.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Intern S2 Preview 397B locally?
Yes — Intern S2 Preview 397B can run locally on consumer hardware. At BF16 quantization it needs 807.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Intern S2 Preview 397B?
At BF16, the download is about 806.85 GB.
- Which GPUs can run Intern S2 Preview 397B?
No single consumer GPU has enough VRAM to run Intern S2 Preview 397B at BF16 (807.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run Intern S2 Preview 397B?
Intern S2 Preview 397B requires at least 807.3 GB at BF16, which exceeds the unified memory of most consumer devices. A high-memory Mac Studio, Mac Pro, or multi-GPU desktop setup is recommended.