LLM EXPLORER 59,278 MODELS INDEXED

RewardAnything 8B V1 by WisdomShell

By WisdomShell · 279 downloads
HF Repo ↗ Copy URL

RewardAnything 8B V1 is an open-source language model by WisdomShell. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.19.

  Arxiv:2506.03637 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b   Conversational   En   Principle-following   Qwen   Qwen3   Region:us   Reward-model   Rlhf   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/WisdomShell/RewardAnything-8B-v1 

RewardAnything 8B V1 Parameters and Internals

LLM NameRewardAnything 8B V1
Repository 🤗https://huggingface.co/WisdomShell/RewardAnything-8B-v1 
Base Model(s)  Qwen3 8B   Qwen/Qwen3-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-07-14
MaintainerWisdomShell
Model Typeqwen3
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.5 GB: 4-of-4
Supported Languagesen zh
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to RewardAnything 8B V1

Best Alternatives
Context / RAM
Downloads
Likes
PaCoRe 8B320K / 1.2 GB5448
RLVR 8B 0926320K / 1.2 GB638
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
...Reason 8B Pretrain Competition128K / 16.8 GB2440
Marco DeepResearch 8B128K / 16.3 GB52027
Note: green Score (e.g. "73.2") means that the model is better than WisdomShell/RewardAnything-8B-v1.