Model library / inclusionAI
Ling-3.1-flash-base is a 560 billion-parameter hybrid MoE base checkpoint from inclusionAI, provided in bfloat16 for further training and research.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
Ling-3.1-flash-base is a base checkpoint of the Ling-3.1-flash family, released by inclusionAI. It contains 560 billion total parameters and uses a hybrid linear Mixture-of-Experts architecture with 512 experts, activating eight routed and one shared expert per token. The model is intended for further pre-training, domain adaptation and research.
The checkpoint is stored in bfloat16 format and occupies roughly 572 billion parameters in memory. It supports a context window of 262 144 tokens. The model is released under the MIT licence, allowing unrestricted use. Deployment will require substantial hardware to handle the parameter count and long context length.
Specification
| Repository | inclusionAI/Ling-3.1-flash-base |
| Publisher | inclusionAI |
| Published | 25 October 2026 |
| Architecture | BailingMoeV3ForCausalLM |
| Model type | bailing_hybrid |
| Parameters | 572,120,680,768 |
| Layers | 72 |
| Hidden size | 4,096 |
| Attention heads | 64, 64 key/value heads |
| Context length | 262,144 tokens |
| Vocabulary | 157,184 tokens |
| Weight format | bfloat16 |
| Licence | mit |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 1065.7 GiB | Full precision as released |
| fp8 | 532.8 GiB | 8-bit, near-lossless on most models |
| int4 | 266.4 GiB | 4-bit, smallest footprint |
The cache costs 2.2 MiB per token at 16-bit, so the full 262,144-token context of one request needs about 576.0 GiB. Concurrency multiplies that number, not the weights.
That figure is an upper bound: this model uses compressed key-value attention, so the real cache is a fraction of the figure above.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | more than 8 | — | — |
| RTX 5090 32GB | more than 8 | — | — |
| L40S 48GB | more than 8 | — | — |
| A100 80GB | more than 8 | — | — |
| H100 80GB | more than 8 | — | — |
| RTX PRO 6000 96GB | more than 8 | — | — |
| H200 141GB | more than 8 | — | — |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve inclusionAI/Ling-3.1-flash-base \ --tensor-parallel-size 8 \ --max-model-len 262144 \ --gpu-memory-utilization 0.90
At the released precision the weights do not fit on eight of the largest cards above, so this needs more than one node, or a quantised build.
Questions
The weights take about 1066 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.
The repository declares mit. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.
Also in the library
Ling-3.1-flash-1019 is a 572.1 billion-parameter causal language model from inclusionAI, designed for advanced reasoning and agen…
Ling-3.0-flash-Sante is a 124-billion-parameter hybrid language model specialised for healthcare reasoning and research.
Ling-3.1-flash is a 572.1 billion-parameter hybrid reasoning language model with a 262,144-token context window.
LLaDA2.2-mini is a 16.3 billion-parameter MoE diffusion language model with 128 k token context, supporting Levenshtein editing.
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.