Ling 3.0 Flash

Introduction

We're introducing Ling-3.0-flash, our next-generation native hybrid reasoning model. Operating with 124B total and 5.1B active parameters (~12.4% and ~8.1% of our previous 1T-class flagship Ring-2.6-1T), Ling-3.0-flash matches or outperforms its predecessor across key benchmarks.

Key highlights of the model are summarized below:

• Native Hybrid-Linear Architecture: Ling-3.0 adopts a native hybrid linear attention architecture from the very start of pretraining (5:1 alternating stacking of Kimi Delta Attention (KDA) and MLA), upgraded with KDA fine-grained diagonal gating and 1/64 sparse MoE. With 124B total parameters and 5.1B activated parameters, it achieves a synergistic leap in long-context efficiency and computational cost.
• Remarkable Efficiency & Performance: Engineered for speed, compute efficiency, and production deployment, Ling-3.0-flash delivers class-defying performance against both larger SOTA competitors and previous-generation flagships. Activating only 5.1B parameters per token, it provides impressive reasoning, instruction following, and long-context capabilities to empower complex agentic workflows in production environments.
• Comprehensive Agentic Evolution: Tailored for real-world productivity workflows, the model incorporates 10,000+ interactive training environments to achieve end-to-end closed-loop execution across Coding, General, and Deep Research Agent tasks. It natively integrates the SGLang HiCache + Mooncake hierarchical caching architecture (featuring physical dual-pools and a cluster-shared L3 cache), eliminating redundant recomputation during long-horizon interactions and reducing Time to First Token (TTFT) by 60% to over 80% in long-input scenarios.

Model Overview

The model summary information and architecture diagram are as follows:

Evaluation

We have conducted a comprehensive evaluation of Ling-3.0-flash across multiple authoritative benchmarks. Ling-3.0-flash performs strongly on representative code/agent benchmarks such as SWE-Bench Pro, SWE-Bench Multilingual, Tau3-banking-AA, MCP-Atlas and SkillsBench, etc. In practice, Ling-3.0-flash delivers a strong user experience across frameworks including Claude Code,Kilo Code,Qwen Code,Hermes Agent,and OpenClaw, etc. Beyond agentic tasks, Ling-3.0-flash also delivers strong performance across general knowledge,mathematical reasoning,instruction following,and long-context understanding.

Quickstart

SGLang

The hardware- and recipe-specific launch matrix (BF16/FP8 × Low-Latency / High-Throughput / HiCache + Mooncake), with a live command generator and verified configurations, lives in the SGLang cookbook:

Cookbook: https://docs.sglang.io/cookbook/autoregressive/InclusionAI/Ling-3.0-flash

Install SGLang

Use the pre-built image that tracks the Ling-3.0 runtime:

docker pull lmsysorg/sglang:dev-Ling-3.0-flash

Run Inference

Recommended low-latency recipe (built-in MTP / NEXTN, 256K YaRN context) on 4× 141GB-class GPUs (H20-3e) or 4-GPU Blackwell nodes:

docker run --rm --gpus all --ipc=host --shm-size 32g \
  -p 30000:30000 \
  -e HF_TOKEN=<your-hf-token> \
  lmsysorg/sglang:dev-Ling-3.0-flash \
  env SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 \
  python3 -m sglang.launch_server \
    --model-path inclusionAI/Ling-3.0-flash \
    --tp 4 \
    --context-length 262144 \
    --speculative-algorithm NEXTN \
    --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":2.0,"rope_theta":6000000,"partial_rotary_factor":0.5,"original_max_position_embeddings":131072}}' \
    --mem-fraction-static 0.8 \
    --host 0.0.0.0 \
    --port 30000

On 80GB cards (H100 / H800) use --tp 8 with the same flags; see the cookbook cell for your hardware.

Client

Thinking is enabled by default by both the chat template and the ling3 reasoning parser. Disable it per request with "chat_template_kwargs": {"enable_thinking": false}. We recommend the sampling parameters temperature=0.6, top_p=0.95, and top_k=20.

curl -s http://localhost:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "inclusionAI/Ling-3.0-flash",
       "messages": [{"role": "user", "content": "hello!"}],
       "stream": true,
       "temperature": 0.6,
       "top_k": 20,
       "top_p": 0.95
     }'

For --reasoning-parser ling3 / --tool-call-parser ling3, the HiCache + Mooncake L3 setup, and GSM8K / bench_serving reproduction commands, see the cookbook page linked above.

vLLM

Install our vLLM

pip install uv

uv venv ~/my_ling_env

source ~/my_ling_env/bin/activate

git clone -b ling_3_0 https://github.com/inclusionAI/vllm-ling-v3.git

cd vllm-ling-v3

VLLM_USE_PRECOMPILED=1 uv pip install --editable . --torch-backend=auto

Run Inference

Here is the example to run Ling-3.0-flash with 4 GPUs, where the server port is ${PORT}:

Server

Since the model is trained with MTP, we recommend enabling MTP during inference (i.e., --speculative-config) for lower latency.

vllm serve "$MODEL_PATH" \
    --port "$PORT" \
    --trust-remote-code \
    --served-model-name auto \
    --tensor-parallel-size 4 \
    --gpu-memory-utilization 0.85 \
    --enable-prefix-caching \
    --mamba-cache-mode align \
    --enable-auto-tool-choice \
    --tool-call-parser ling3 \
    --reasoning-parser ling3 \
    --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

Client

We recommend using the sampling parameters temperature=0.6, top_p=0.95, and top_k=20, and enabling enable_thinking for better performance.

curl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "auto",
       "messages": [{"role": "user", "content": "hello!"}],
       "chat_template_kwargs": {"enable_thinking": true},
       "stream": true,
       "temperature": 0.6, 
       "top_k": 20,
       "top_p": 0.95
     }'