AxForge
Sign in Get started

Model reference · open weights

Skywork-VL-Reward

LLMs Skywork Vision + text 1 build Open weights 3k dl/mo

Skywork-VL-Reward is an open-weight language model from Skywork. Skywork-VL-Reward-7B (BF16) weighs 16.6 GB; the smallest configuration that runs it is RTX 4090 24 GB.

  • Skywork-VL-Reward is an 8.3B parameter multimodal reward model developed by Skywork for image-text-to-text tasks.
  • It is based on the Qwen2.5-VL-7B-Instruct architecture with an added value head and is released under the MIT license.
  • The model achieved a score of 73.1 on VL-RewardBench and 90.1 on RewardBench.

Summary of the Skywork/Skywork-VL-Reward-7B model card, 2026-10-05

Hugging Face ↗Paper ↗

What it is

Released bySkywork
Released2025-04-14
Parameters8.3B
VRAM16.6 GB for the weights

What it runs on

Memory and cards for Skywork-VL-Reward-7B (BF16)

16.6 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards		does not fit
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms