finbert vs Qwen2.5-Math-PRM-7B

Specs, VRAM requirements and download trends — updated 6 August 2026.

ProsusAI · A
Params
Context
512
30d
5.6 M
Qwen · B
Params
7.6 B
Context
4,096
30d
249 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification finbert Qwen2.5-Math-PRM-7B
Parameters 7.6 B
Architecture BertForSequenceClassification Qwen2ForProcessRewardModel
Context length 512 4,096
Licence other
Commercial use Unknown Unknown
Languages 1 2
Downloads 30d 5,552,674 249,372
Downloads all time 112.5 M 1.4 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2025-01-13

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

6.5 M241 K
finbert Qwen2.5-Math-PRM-7B

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Qwen2.5-Math-PRM-7B · fp16 18.4 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons