Theme
AI Resources
LongCat 2.0
LongCat 2.0 is Meituan LongCat's open-weights MoE language model release for coding, long-context work, and agent-style software tasks.
The model card describes 1.6 trillion total parameters, about 48 billion active per token, native 1M-token context, and base, FP8, and INT8 Hugging Face model pages. Treat the benchmark tables and integration claims as Meituan-reported until tested. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
A very large MoE language model
LongCat 2.0 is a sparse mixture-of-experts language model trained on more than 35 trillion tokens. The official materials focus on coding, repository-level edits, long-horizon tasks, search, productivity, and agentic workflows.
Why it stands out
Public weights with multiple serving paths
Technical readers can compare the base, FP8, and INT8 Hugging Face pages, the GitHub model-card repository, ModelScope listing, tokenizer template notes, and vLLM or SGLang serving examples before choosing a test path.
Availability
Open weights, official chat, heavy local setup
Hugging Face lists the model under an MIT license and shows no active HF Inference Provider deployment. The model card links an official chat website, while local serving is aimed at large multi-GPU or NPU setups.
Why it matters
What makes it useful
LongCat 2.0 gives technical readers a large open-weights model to test against coding-agent and long-context workloads instead of only reading benchmark tables. The value is the combination of public model files, quantized variants, chat-template notes, and serving examples for teams comparing how much work they can keep outside one hosted provider.
What to know
Where it fits
LongCat 2.0 suits technical teams comparing very large coding models by model shape, serving burden, tokenizer behavior, and hosted versus self-run access. It is not a casual local model or a no-setup productivity app.
Notable points
What stands out
The GitHub README and Hugging Face model card report LongCat Sparse Attention, a 135B-parameter N-gram Embedding module, more than 35T training tokens, native 1M context, in-house benchmark tables, and GPU or NPU deployment notes. Treat the architecture and performance details as Meituan-reported claims.
Before using
What to review
Which path you actually need: official chat, API platform, Hugging Face base weights, FP8 weights, INT8 weights, ModelScope, vLLM, SGLang, GPU deployment, or NPU deployment.
Hardware and storage requirements. Hugging Face lists the base model at about 3.55 TB and the FP8 and INT8 variants at about 2.05 TB and 2.06 TB, while the model card gives a 16x H20 GPU deployment example.
Current API limits, account requirements, data handling, and terms before sending private prompts, code, files, or customer data through any hosted route.
The repository identifies the model under the MIT License. Review the current terms at the source to decide whether they suit your intended use, and check any separate terms for hosted access.
Generated-code review, tests, security checks, dependency review, and human approval before connecting any model to repositories, terminals, browsers, credentials, or production systems.
The README says LongCat works with Claude Code, OpenClaw, and Hermes, but the model-card repository does not provide step-by-step setup for those harnesses. Verify the actual provider and configuration path before relying on that claim.
Benchmark and performance claims as project-reported numbers to verify against your own workload, especially for coding-agent tasks.
Reader fit
Who may find it relevant
Technical readers comparing large open-weights language models for coding, long-context, and agentic workflows.
Builders who want to test the same model family across base, FP8, INT8, Hugging Face, ModelScope, vLLM, SGLang, or official LongCat access paths.
Teams deciding whether a very large model release is worth the serving cost, storage, setup, and review work.
Less relevant for readers who want a small local model, a finished consumer chatbot, or a coding assistant that works without setup.
Editorial note
Why LifeHubber lists it
LongCat 2.0 puts a very large coding and agentic model into public model files with quantized variants and serving notes. Technical readers can test model behavior, setup cost, and provider-dependence tradeoffs instead of relying only on benchmark tables.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Compare another large coding model before choosing a serving path.
LongCat 2.0 brings 1M context and a very large open-weight footprint. Continue with another long-horizon coding model, or browse model families by capability and access route.
More in AI Models
Keep browsing this category
Explore more AI model resources.
Gemma 4
google/gemma-4
A Google DeepMind Gemma 4 model family collection with public checkpoints including Gemma 4 12B, a dense multimodal model Google describes around local agentic workflows, native audio input, and encoder-free vision/audio handling.
Hy4 preview
tencent/Hy4-preview
Tencent Hy Team's preview-stage 770B-total, 49B-active Mixture-of-Experts language model for coding, document and analysis work, game development, research, tool use, and long-context tasks, with a 1M-token context window, public BF16 and FP8 weights, and dedicated vLLM or SGLang deployment paths.
LTX-2.5
Lightricks/LTX-2.5
A Lightricks audio-video model family with gated component weights, synchronized sound, text-to-video, image-to-video, multishot generation, local Python and ComfyUI paths, fine-tuning tools, and a separate hosted API.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
