What are the hardware requirements for BFS Prover V2 32B?

BFS Prover V2 32B requires approximately 131.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed BFS Prover V2 32B and how large is it?

BFS Prover V2 32B is developed by ByteDance-Seed, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate BFS Prover V2 32B?

BFS Prover V2 32B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

BFS Prover V2 32B by ByteDance-Seed — VRAM 131.5GB, 128K context

Name: BFS Prover V2 32B
Author: ByteDance-Seed

BFS Prover V2 32B is an open-source language model by ByteDance-Seed. Features: 32b LLM, VRAM: 131.5GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.21.

Arxiv:2509.06493 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b Lean4 Qwen2 Region:us Safetensors Sharded Step-prover Tensorflow

Model Card on HF 🤗: https://huggingface.co/ByteDance-Seed/BFS-Prover-V2-32B

BFS Prover V2 32B Parameters and Internals

LLM Name	BFS Prover V2 32B
Repository 🤗	https://huggingface.co/ByteDance-Seed/BFS-Prover-V2-32B
Base Model(s)	Qwen/Qwen2.5-32B Qwen/Qwen2.5-32B
Model Size	32b
Required VRAM	131.5 GB
Updated	2026-08-08
Maintainer	ByteDance-Seed
Model Type	qwen2
Model Files	4.5 GB: 1-of-29 4.7 GB: 2-of-29 4.5 GB: 3-of-29 4.5 GB: 4-of-29 4.7 GB: 5-of-29 4.5 GB: 6-of-29 4.5 GB: 7-of-29 4.7 GB: 8-of-29 4.5 GB: 9-of-29 4.5 GB: 10-of-29 4.7 GB: 11-of-29 4.5 GB: 12-of-29 4.5 GB: 13-of-29 4.7 GB: 14-of-29 4.5 GB: 15-of-29 4.5 GB: 16-of-29 4.7 GB: 17-of-29 4.5 GB: 18-of-29 4.5 GB: 19-of-29 4.7 GB: 20-of-29 4.5 GB: 21-of-29 4.5 GB: 22-of-29 4.7 GB: 23-of-29 4.5 GB: 24-of-29 4.5 GB: 25-of-29 4.7 GB: 26-of-29 4.5 GB: 27-of-29 4.5 GB: 28-of-29 3.7 GB: 29-of-29
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.52.4
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	float32
Errors	replace

Rank the BFS Prover V2 32B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to BFS Prover V2 32B

Best Alternatives	Context / RAM	Downloads	Likes
Openbuddy Qwq 32B V24.2 200K	195K / 65.8 GB	9	3
Openbuddy Qwq 32B V24.1 200K	195K / 65.8 GB	10	3
Openbuddy Qwq 32B V25.2q 200K	195K / 65.8 GB	1	4
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
DeepSeek R1 Distill Qwen 32B	128K / 65.7 GB	841633	1584
Qwen2.5 32B	128K / 65.5 GB	49206	180
RomboUltima 32B	128K / 20.7 GB	12	6
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	42	17
Ultiima 32B	128K / 65.8 GB	11	7
...wen2.5 32B Inst BaseMerge TIES	128K / 65.8 GB	13	4

Note: green Score (e.g. "73.2") means that the model is better than ByteDance-Seed/BFS-Prover-V2-32B.