LLM EXPLORER 57,252 MODELS INDEXED

Ring Flash Linear 2.0 GPTQ Int4 by inclusionAI

By inclusionAI · 19 downloads
HF Repo ↗ Copy URL

Ring Flash Linear 2.0 GPTQ Int4 is an open-source language model by inclusionAI. Features: 15.4b LLM, VRAM: 56.5GB, Context: 128K, License: mit, MoE, Quantized, LLM Explorer Score: 0.2.

  Arxiv:2510.19338   Bailing moe linear Base model:inclusionai/ring-mi... Base model:quantized:inclusion...   Compressed-tensors   Conversational   Custom code   En   Gptq   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inclusionAI/Ring-flash-linear-2.0-GPTQ-int4 

Ring Flash Linear 2.0 GPTQ Int4 Parameters and Internals

LLM NameRing Flash Linear 2.0 GPTQ Int4
Repository 🤗https://huggingface.co/inclusionAI/Ring-flash-linear-2.0-GPTQ-int4 
Base Model(s)  inclusionAI/Ring-mini-linear-2.0   inclusionAI/Ring-mini-linear-2.0
Model Size15.4b
Required VRAM56.5 GB
Updated2026-08-08
MaintainerinclusionAI
Model Typebailing_moe_linear
Model Files  5.0 GB: 1-of-12   5.0 GB: 2-of-12   5.0 GB: 3-of-12   5.0 GB: 4-of-12   5.0 GB: 5-of-12   5.0 GB: 6-of-12   5.0 GB: 7-of-12   5.0 GB: 8-of-12   5.0 GB: 9-of-12   5.0 GB: 10-of-12   5.0 GB: 11-of-12   1.5 GB: 12-of-12
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureBailingMoeLinearV2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.55.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size157184
Torch Data Typebfloat16