Ling 2.6 Flash is an open-source language model by inclusionAI. Features: 107.5b LLM, VRAM: 208.2GB, Context: 128K, License: mit, LLM Explorer Score: 0.41.
Arxiv:2606.15079 Bailing hybrid Conversational Custom code En Eval-results Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/inclusionAI/Ling-2.6-flash
Ling 2.6 Flash Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Ling 2.6 Flash Parameters and Internals
| LLM Name | Ling 2.6 Flash |
| Repository 🤗 | https://huggingface.co/inclusionAI/Ling-2.6-flash |
| Model Size | 107.5b |
| Required VRAM | 208.2 GB |
| Updated | 2026-07-03 |
| Maintainer | inclusionAI |
| Model Type | bailing_hybrid |
| Model Files | |
| Supported Languages | en |
| Model Architecture | BailingMoeV2_5ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.56.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 157184 |
| Torch Data Type | bfloat16 |
Quantized Models of the Ling 2.6 Flash
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Ling 2.6 Flash Mlx 4bit DWQ | 4 | 351 | 58 GB |
| Ling 2.6 Flash MLX 9bit | 2 | 91 | 117 GB |
| Ling 2.6 Flash Mlx 4bit | 2 | 53 | 58 GB |
| Ling 2.6 Flash Mlx 4bit Gs32 | 2 | 24 | 65 GB |
Rank the Ling 2.6 Flash Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54724 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a