Ling-1T-GGUF

Image: image

🤗 Hugging Face   |   🤖 ModelScope   |   🐙 Experience Now

Introduction#

Ling-1T is the first flagship non-thinking model in the Ling 2.0 series, featuring 1 trillion total parameters with ≈ 50 billion active parameters per token. Built on the Ling 2.0 architecture, Ling-1T is designed to push the limits of efficient reasoning and scalable cognition.

Pre-trained on 20 trillion+ high-quality, reasoning-dense tokens, Ling-1T-base supports up to 128K context length and adopts an evolutionary chain-of-thought (Evo-CoT) process across mid-training and post-training. This curriculum greatly enhances the model’s efficiency and reasoning depth, allowing Ling-1T to achieve state-of-the-art performance on multiple complex reasoning benchmarks—balancing accuracy and efficiency.

Flagship-Level Efficient Reasoning#

Image: image

Image: image

We comprehensively evaluated Ling-1T against leading flagship models, including both open-source giants (e.g., DeepSeek-V3.1-Terminus, Kimi-K2-Instruct-0905) and closed-source APIs (GPT-5-main, Gemini-2.5-Pro). Across code generation, software development, competition-level mathematics, professional math, and logical reasoning, Ling-1T consistently demonstrates superior complex reasoning ability and overall advantage.

In the AIME 25 benchmark, Ling-1T extends the Pareto frontier of reasoning accuracy vs. reasoning length, showcasing its strength in “efficient thinking and precise reasoning.”

Image: image

Aesthetic Understanding and Front-End Generation#

Ling-1T excels in visual reasoning and front-end code generation tasks, combining deep semantic understanding with precise code synthesis. We introduce a hybrid Syntax–Function–Aesthetics reward mechanism, enabling the model to not only generate correct and functional code but also demonstrate a refined sense of visual aesthetics. On ArtifactsBench, Ling-1T ranks first among open-source models, and the benchmark visualizations in this card were, in fact, generated by Ling-1T itself.

Emergent Intelligence at Trillion-Scale#

Scaling to the trillion-parameter level has revealed strong emergent reasoning and transfer capabilities. For example, in the BFCL V3 tool-use benchmark, Ling-1T achieves ≈ 70% tool-call accuracy with only light instruction tuning—despite having seen no large-scale trajectory data during training. Ling-1T can:

• Interpret complex natural-language instructions
• Transform abstract logic into functional visual components
• Generate cross-platform compatible front-end code
• Create stylistically controlled marketing copy and multi-lingual text

These capabilities form the foundation for general, collaborative human–AI intelligence, which we aim to advance together with the open-source community through Ling-1T’s release.

Pre-Training at Trillion Scale#

The Ling 2.0 architecture was designed from the ground up for trillion-scale efficiency, guided by the Ling Scaling Law (arXiv:2507.17702). This ensures architectural and hyperparameter scalability even under 1e25–1e26 FLOPs of compute.

Key architectural innovations include:

• 1T total / 50B active parameters with a 1/32 MoE activation ratio
• MTP layers for enhanced compositional reasoning
• Aux-loss-free, sigmoid-scoring expert routing with zero-mean updates
• QK Normalization for fully stable convergence

Image: image

Ling-1T is the largest FP8-trained foundation model known to date. FP8 mixed-precision training yields 15%+ end-to-end speedup, improved memory efficiency, and maintains ≤ 0.1% loss deviation from BF16 across 1T tokens. A fine-grained, heterogeneous 1F1B interleaved pipeline further boosts utilization by 40 %+. System-level optimizations—fused kernels, communication scheduling, recomputation, checkpointing, simulation, and telemetry—ensure stable trillion-scale training.

Image: image

Pre-training used over 20T high-quality tokens, with > 40% reasoning-dense data in later stages. Mid-training introduced curated chain-of-thought corpora for “reasoning pre-activation”, improving downstream reasoning stability. A custom WSM (Warmup–Stable–Merge) LR scheduler（arXiv:2507.17634） with mid-train checkpoint merging simulates LR decay and boosts generalization.

Post-Training and Evo-CoT Optimization#

Built upon mid-training reasoning activation, post-training adopts Evo-CoT (Evolutionary Chain-of-Thought) for progressive reasoning enhancement under controllable cost. This approach continually expands the Pareto frontier of reasoning accuracy vs. efficiency—ideal for reflexive non-thinking models.

For reinforcement learning, we introduce LPO (Linguistics-Unit Policy Optimization) —a novel sentence-level policy optimization method. Unlike GRPO (token-level) or GSPO (sequence-level) algorithms, LPO treats sentences as the natural semantic action units, enabling precise alignment between rewards and reasoning behavior. Empirically, LPO offers superior training stability and generalization across reasoning tasks.

Image: image

Image: image

Evaluation#

Ling-1T has been extensively evaluated across knowledge, code, math, reasoning, agent, and alignment benchmarks. It currently stands as the best open-source flagship non-thinking model, rivaling closed-source APIs in complex reasoning while maintaining exceptional efficiency and interpretability.

Image: image

Model Downloads#

You can download Ling-1T from the following table. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process.

Note: If you are interested in previous version, please visit the past model collections in Huggingface or ModelScope.

Quickstart#

🚀 Try Online#

You can experience Ling-1T online at: ZenMux

🔌 API Usage#

You can also use Ling-1T through API calls:

from openai import OpenAI

# 1. Initialize the OpenAI client
client = OpenAI(
    # 2. Point the base URL to the ZenMux endpoint
    base_url="https://zenmux.ai/api/v1",
    # 3. Replace with the API Key from your ZenMux user console
    api_key="<your ZENMUX_API_KEY>",
)

# 4. Make a request
completion = client.chat.completions.create(
    # 5. Specify the model to use in the format "provider/model-name"
    model="inclusionai/ling-1t",
    messages=[
        {
            "role": "user",
            "content": "What is the meaning of life?"
        }
    ]
)

print(completion.choices[0].message.content)

Deployment#

SGLang#

Environment Preparation#

We will later submit our model to the SGLang official release. Now we can prepare the environment by following these steps:

pip3 install -U sglang sgl-kernel

Run Inference#

Both BF16 and FP8 models are supported by SGLang now. It depends on the dtype of the model in ${MODEL_PATH}.

Here is the example to run Ling-1T with multiple GPU nodes, where the master node IP is ${MASTER_IP} and server port is ${PORT}:

• Start server:

# Node 0:
python -m sglang.launch_server --model-path $MODEL_PATH --tp-size 8 --pp-size 4 --dp-size 1 --trust-remote-code --dist-init-addr $MASTER_IP:2345 --port $PORT --nnodes 4 --node-rank 0 

# Node 1:
python -m sglang.launch_server --model-path $MODEL_PATH --tp-size 8 --pp-size 4 --dp-size 1 --trust-remote-code --dist-init-addr $MASTER_IP:2345 --port $PORT --nnodes 4 --node-rank 1 

# Node 2:
python -m sglang.launch_server --model-path $MODEL_PATH --tp-size 8 --pp-size 4 --dp-size 1 --trust-remote-code --dist-init-addr $MASTER_IP:2345 --port $PORT --nnodes 4 --node-rank 2 

# Node 3:
python -m sglang.launch_server --model-path $MODEL_PATH --tp-size 8 --pp-size 4 --dp-size 1 --trust-remote-code --dist-init-addr $MASTER_IP:2345 --port $PORT --nnodes 4 --node-rank 3

# This is only an example. Please adjust arguments according to your actual environment.

• Client:

curl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "What is the capital of France?"}]}'

More usage can be found here

vLLM#

Environment Preparation#

pip install vllm==0.11.0

Run Inference:#

Here is the example to deploy the model with multiple GPU nodes, where the master node IP is ${MASTER_IP}, server port is ${PORT} and the path of model is ${MODEL_PATH}:

# step 1. start ray on all nodes

# step 2. start vllm server only on node 0:
vllm serve $MODEL_PATH --port $PORT --served-model-name my_model --trust-remote-code --tensor-parallel-size 8 --pipeline-parallel-size 4 --gpu-memory-utilization 0.85

# This is only an example, please adjust arguments according to your actual environment.

To handle long context in vLLM using YaRN, we need to follow these two steps:

1. Add a rope_scaling field to the model's config.json file, for example:

{
  ...,
  "rope_scaling": {
    "factor": 4.0,
    "original_max_position_embeddings": 32768,
    "type": "yarn"
  }
}

1. Use an additional parameter --max-model-len to specify the desired maximum context length when starting the vLLM service.

For detailed guidance, please refer to the vLLM instructions.

Limitations & Future Plans#

While Ling-1T has made strong progress in efficient reasoning, cross-domain generalization, and training efficiency, several limitations remain:

• GQA-based attention: stable for long-context reasoning but relatively costly. Future versions will adopt hybrid attention to improve efficiency.
• Limited agentic ability: current model has room to grow in multi-turn interaction, long-term memory, and tool use.
• Instruction and identity issues: occasional deviations or role confusion may occur; future updates will enhance alignment and consistency.

The future versions of Ling-1T will continue to evolve in architecture, reasoning, and alignment, advancing the series toward more general intelligence.

License#

This code repository is licensed under the MIT License.

FAQ#

Recommended temperature? 0.7 Recommended top_p? 0.95