RADAR-Vicuna-7B vs Qwen2.5-Math-PRM-7B

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

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

Specification comparison

Differences are highlighted; identical values are muted.

Specification RADAR-Vicuna-7B Qwen2.5-Math-PRM-7B
Parameters 7.6 B
Architecture RobertaForSequenceClassification Qwen2ForProcessRewardModel
Context length 512 4,096
Licence other
Commercial use Unknown Unknown
Languages 2
Downloads 30d 1,021,915 249,372
Downloads all time 8.2 M 1.4 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2023-06-24 2025-01-13

Download trend

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

1.1 M241 K
RADAR-Vicuna-7B 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