LLM EXPLORER 60,587 MODELS INDEXED

RLT 32B by SakanaAI

By SakanaAI · 10 downloads
HF Repo ↗ Copy URL

RLT 32B is an open-source language model by SakanaAI. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.18.

  Arxiv:2502.07374   Arxiv:2506.08388 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b-in...   Code   Conversational   Distillation   En   Instruct   Learning   Math   Qwen2   Reasoning   Region:us   Reinforcement   Rlt   Safetensors   Science   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/SakanaAI/RLT-32B 

RLT 32B Parameters and Internals

LLM NameRLT 32B
Repository 🤗https://huggingface.co/SakanaAI/RLT-32B 
Base Model(s)  Qwen/Qwen2.5-32B-Instruct   Qwen/Qwen2.5-32B-Instruct
Model Size32b
Required VRAM65.8 GB
Updated2026-07-04
MaintainerSakanaAI
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesen zh
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to RLT 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 GB4217
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB594
Franqwenstein 35B128K / 69.8 GB58
ELYZA Thinking 1.0 Qwen 32B128K / 65.8 GB2310
Archaeo 32B KTO128K / 65.8 GB174
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 SakanaAI/RLT-32B.