Intern-S1-Pro
Intern-S1-Pro is an open-weight vision and language model from Shanghai AI Lab (InternLM) with 917B parameters (mixture of experts). At 4-bit it needs about 607 GB of memory, more than any single device in our directory has.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- Shanghai AI Lab (InternLM)
- Released
- 2 Feb 2026
- Parameters
- 917B · MoE
- Type
- Vision and language
- Context
- 262,144 tokens
- License
- Apache-2.0
- HF downloads, 30 days
- 7,381
- Repository
- internlm/Intern-S1-Pro
More from Shanghai AI Lab (InternLM)
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 607 GB |
| Q8 | 1071 GB |
| BF16 | 2019.2 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 607 GB | Too big 1686% | No single device in our directory has enough memory |
| 8-bit (Q8) | ≈ 1071 GB | Too big 2975% | No single device in our directory has enough memory |
| 16-bit (BF16) | ≈ 2019.2 GB | Too big 5609% | No single device in our directory has enough memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
Through an API
No hosted API found.
More about this model
Frequently asked questions
How much memory does Intern-S1-Pro need? At an 8k context, about 607 GB at 4-bit, 1071 GB at 8-bit and 2019.2 GB at 16-bit (BF16). A longer context needs more.
Can I run Intern-S1-Pro on a Mac? No Mac in our directory has enough usable memory for the 4-bit estimate of 607 GB. We have not found a trusted MLX or GGUF build yet.
Does the full context fit? Intern-S1-Pro supports up to 262,144 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card.