LLM EXPLORER 63,529 MODELS INDEXED

RSR 27B by IntelligenceLab

By IntelligenceLab · 74 downloads
HF Repo ↗ Copy URL

RSR 27B is an open-source language model by IntelligenceLab. Features: 27b LLM, VRAM: 53.8GB, License: apache-2.0, LLM Explorer Score: 0.28.

  Conversational   Endpoints compatible   Image-text-to-text   Qwen   Qwen3 5   Recursive-self-rewrite   Region:us   Rsr   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/IntelligenceLab/RSR-27B 

RSR 27B Parameters and Internals

LLM NameRSR 27B
Repository 🤗https://huggingface.co/IntelligenceLab/RSR-27B 
Model Size27b
Required VRAM53.8 GB
Updated2026-10-09
MaintainerIntelligenceLab
Model Typeqwen3_5
Model Files  4.6 GB: 1-of-16   3.4 GB: 2-of-16   5.4 GB: 3-of-16   1.5 GB: 4-of-16   5.3 GB: 5-of-16   4.7 GB: 6-of-16   5.3 GB: 7-of-16   0.4 GB: 8-of-16   5.2 GB: 9-of-16   0.8 GB: 10-of-16   5.2 GB: 11-of-16   0.6 GB: 12-of-16   5.2 GB: 13-of-16   0.3 GB: 14-of-16   5.2 GB: 15-of-16   0.7 GB: 16-of-16   0.9 GB   0.8 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to RSR 27B

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB863
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB95131835
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Note: green Score (e.g. "73.2") means that the model is better than IntelligenceLab/RSR-27B.