LLM EXPLORER 59,516 MODELS INDEXED

Light R1 32B by qihoo360

By qihoo360 · 22 downloads
HF Repo ↗ Copy URL

Light R1 32B is an open-source language model by qihoo360. Features: 32b LLM, VRAM: 65.6GB, Context: 41K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

  Arxiv:2503.10460 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b-in...   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/qihoo360/Light-R1-32B 

Light R1 32B Parameters and Internals

LLM NameLight R1 32B
Repository 🤗https://huggingface.co/qihoo360/Light-R1-32B 
Base Model(s)  Qwen/Qwen2.5-32B-Instruct   Qwen/Qwen2.5-32B-Instruct
Model Size32b
Required VRAM65.6 GB
Updated2026-08-04
Maintainerqihoo360
Model Typeqwen2
Instruction-BasedYes
Model Files  3.5 GB: 1-of-14   4.7 GB: 2-of-14   5.0 GB: 3-of-14   4.8 GB: 4-of-14   4.8 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.8 GB: 8-of-14   5.0 GB: 9-of-14   4.9 GB: 10-of-14   4.8 GB: 11-of-14   4.8 GB: 12-of-14   5.0 GB: 13-of-14   3.7 GB: 14-of-14
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length42768
Model Max Length42768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Light R1 32B

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB92
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB2817
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB224
Franqwenstein 35B128K / 69.8 GB58
ELYZA Thinking 1.0 Qwen 32B128K / 65.8 GB2310
Archaeo 32B KTO128K / 65.8 GB194
Hamanasu Magnum QwQ 32B128K / 65.8 GB2959
Qwen2.5 32B Gokgok Step3128K / 65.7 GB60
Openthaigpt R1 32B Instruct128K / 65.8 GB338
Qwen2.5 32B Dark Days Stage2128K / 65.8 GB90
Note: green Score (e.g. "73.2") means that the model is better than qihoo360/Light-R1-32B.