LLM EXPLORER 59,694 MODELS INDEXED

Spatial SSRL 7B by internlm

By internlm · 105 downloads

Spatial SSRL 7B is an open-source language model by internlm. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

  Arxiv:2510.27606 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-...   Conversational Dataset:internlm/spatial-ssrl-...   En   Endpoints compatible   Image-text-to-text   Instruct   Multimodal   Qwen2 5 vl   Region:us   Safetensors   Self-supervised learning   Sharded   Spatial   Sptial understanding   Tensorflow

Spatial SSRL 7B Parameters and Internals

LLM NameSpatial SSRL 7B
Repository πŸ€—https://huggingface.co/internlm/Spatial-SSRL-7B 
Base Model(s)  Qwen/Qwen2.5-VL-7B-Instruct   Qwen/Qwen2.5-VL-7B-Instruct
Model Size7b
Required VRAM16.6 GB
Updated2026-08-10
Maintainerinternlm
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  4.4 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.3 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.55.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Spatial SSRL 7B

Best Alternatives
Context / RAM
Downloads
Likes
OmniLong Qwen2.5 VL 7B512K / 16.6 GB72
Qwen2.5 VL 7B Instruct125K / 16.7 GB87409051666
OlmOCR 2 7B 1025 FP8125K / 10 GB540426253
OlmOCR 2 7B 1025125K / 16.6 GB244728157
RolmOCR125K / 16.6 GB224280589
Zoom IQA 7B125K / 16.6 GB141
Qwen2.5 VL 7B Instruct FP4125K / 7.2 GB491653
Embodied Navigator 7B GRPO125K / 17.3 GB201
OlmOCR 7B 0825 FP8125K / 10 GB3801110
PosterCopilot125K / 16.7 GB291
Note: green Score (e.g. "73.2") means that the model is better than internlm/Spatial-SSRL-7B.