LLM EXPLORER 58,133 MODELS INDEXED

Ling 3.0 Flash MXFP4 by olka-fi

By olka-fi · 1399 downloads
HF Repo ↗ Copy URL

Ling 3.0 Flash MXFP4 is an open-source language model by olka-fi. Features: 127.5b LLM, VRAM: 77.9GB, Context: 128K, License: mit, LLM Explorer Score: 0.34.

  8-bit   Bailing hybrid Base model:inclusionai/ling-3.... Base model:quantized:inclusion...   Compressed-tensors   Conversational   Custom code   Hybrid-linear-attention   Moe   Mxfp4   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/olka-fi/Ling-3.0-flash-MXFP4 

Ling 3.0 Flash MXFP4 Parameters and Internals

LLM NameLing 3.0 Flash MXFP4
Repository 🤗https://huggingface.co/olka-fi/Ling-3.0-flash-MXFP4 
Base Model(s)  inclusionAI/Ling-3.0-flash   inclusionAI/Ling-3.0-flash
Model Size127.5b
Required VRAM77.9 GB
Updated2026-08-11
Maintainerolka-fi
Model Typebailing_hybrid
Model Files  8.2 GB: 1-of-24   2.8 GB: 2-of-24   2.8 GB: 3-of-24   2.9 GB: 4-of-24   2.8 GB: 5-of-24   2.8 GB: 6-of-24   2.8 GB: 7-of-24   2.9 GB: 8-of-24   2.8 GB: 9-of-24   2.8 GB: 10-of-24   2.8 GB: 11-of-24   2.9 GB: 12-of-24   2.8 GB: 13-of-24   2.8 GB: 14-of-24   2.8 GB: 15-of-24   2.9 GB: 16-of-24   2.8 GB: 17-of-24   2.8 GB: 18-of-24   2.8 GB: 19-of-24   2.9 GB: 20-of-24   2.8 GB: 21-of-24   2.8 GB: 22-of-24   2.8 GB: 23-of-24   7.6 GB: 24-of-24
Model ArchitectureBailingMoeV3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size157184
Torch Data Typebfloat16

Best Alternatives to Ling 3.0 Flash MXFP4

Best Alternatives
Context / RAM
Downloads
Likes
Ling 3.0 Flash256K / 254.5 GB4189213
Ling 3.0 Flash Int4256K / 77.6 GB19699
Ling 3.0 Flash Fp8256K / 129.3 GB139526
...0 Flash CIRU Int4 Strix Native256K / 77.6 GB477
Note: green Score (e.g. "73.2") means that the model is better than olka-fi/Ling-3.0-flash-MXFP4.