StepFun-Prover-Preview-32B
StepFun-Prover-Preview-32B is an open-weight language model from StepFun with 32.8B parameters. At 4-bit it needs about 24 GB of memory, so the smallest current device that fits it is the Radeon AI PRO R9700.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- StepFun
- Released
- 13 Aug 2025
- Parameters
- 32.8B
- Type
- Language
- Context
- 131,072 tokens
- License
- Apache-2.0
- HF downloads, 30 days
- 1,524
- Repository
- stepfun-ai/StepFun-Prover-Preview-32B
More from StepFun
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 24 GB |
| Q8 | 40.6 GB |
| BF16 | 74.4 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) | ≈ 24 GB | Fits 67% | Radeon AI PRO R970032 GB memory |
| 8-bit (Q8) | ≈ 40.6 GB | Too big 113% | L40S48 GB memory |
| 16-bit (BF16) | ≈ 74.4 GB | Too big 207% | RTX PRO 6000 Blackwell96 GB 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 StepFun-Prover-Preview-32B need? At an 8k context, about 24 GB at 4-bit, 40.6 GB at 8-bit and 74.4 GB at 16-bit (BF16). A longer context needs more.
Can I run StepFun-Prover-Preview-32B on a Mac? The smallest current Mac that fits the 4-bit estimate of 24 GB is the Mac mini M5 Pro (48GB). We have not found a trusted MLX or GGUF build yet.
Does the full context fit? StepFun-Prover-Preview-32B supports up to 131,072 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.