LLM EXPLORER 56,604 MODELS INDEXED

StepFun Prover Preview 32B by stepfun-ai

By stepfun-ai · 68 downloads
HF Repo ↗ Copy URL

StepFun Prover Preview 32B is an open-source language model by stepfun-ai. Features: 32b LLM, VRAM: 65.5GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.2.

Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Chat   Conversational   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stepfun-ai/StepFun-Prover-Preview-32B 

StepFun Prover Preview 32B Parameters and Internals

LLM NameStepFun Prover Preview 32B
Repository 🤗https://huggingface.co/stepfun-ai/StepFun-Prover-Preview-32B 
Base Model(s)  DeepSeek R1 Distill Qwen 32B   deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Model Size32b
Required VRAM65.5 GB
Updated2026-08-08
Maintainerstepfun-ai
Model Typeqwen2
Model Files  12.8 GB: 1-of-5   13.7 GB: 2-of-5   14.2 GB: 3-of-5   13.9 GB: 4-of-5   10.9 GB: 5-of-5
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to StepFun Prover Preview 32B

Best Alternatives
Context / RAM
Downloads
Likes
Openbuddy Qwq 32B V24.2 200K195K / 65.8 GB93
Openbuddy Qwq 32B V24.1 200K195K / 65.8 GB103
Openbuddy Qwq 32B V25.2q 200K195K / 65.8 GB14
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB92
DeepSeek R1 Distill Qwen 32B128K / 65.7 GB8416331584
Qwen2.5 32B128K / 65.5 GB49206180
RomboUltima 32B128K / 20.7 GB126
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB4217
Ultiima 32B128K / 65.8 GB117
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB134
Note: green Score (e.g. "73.2") means that the model is better than stepfun-ai/StepFun-Prover-Preview-32B.