LongCat-2.0
Official · BF16 · safetensors
Runtime certified: SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
LongCat · General · LongCat 2.0
LongCat 2.0: Specs, GPU requirements, hosting & deployment
LongCat 2.0 is a current General release in the LongCat family, certified from its immutable official source revision.
Total parameters1,600.0B
Active parameters48.0B
Context window1,048,576 tokens
Release statusCurrent · Current
ArchitectureLongcatCausalLM
ModalitiesText
LicenseMIT License
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-07-05
Architecture, strengths and use cases
LongCat 2.0 is an official self-hostable Meituan release in the LongCat General track. It uses LongcatCausalLM, carries 1600B / 48B MoE, supports a verified context window of 1,048,576 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
LongCat 2.0 uses LongcatCausalLM with 1600B / 48B MoE. The stored architecture profile records 38 layers, hidden width 8192, 64 attention heads and a 1,048,576 token context ceiling where the official configuration publishes those fields.
Verified LongcatCausalLM architecture
1,048,576 token certified context
Official BF16, FP8, INT8, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
LongCat-2.0-FP8
meituan-longcat/LongCat-2.0-FP8
Official · FP8 · safetensors
Runtime certified: SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
LongCat-2.0-INT8
meituan-longcat/LongCat-2.0-INT8
Official · INT8 · safetensors
Runtime certified: SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| INT8 | safetensors | 8 | Official | Runtime certified |
Recommended hardware
Use only the listed sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory3069.64 GB
KV cache1.19 GB
Runtime overhead609.39 GB
Total with safety margin4563.47 GB
Technically compatible reference sizing
No current FusionPointAI inventory passes every runtime, architecture, topology and memory gate for this exact checkpoint. Use the estimator for global compatible hardware.
License and self-hosting considerations
The full 1600B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
LongCat 2.0 is published under MIT License. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
LongCat-2.0, LongCat-2.0-INT8, LongCat-2.0-FP8
Release timeline
meituan-longcat/longcat/longcat-2 @ 413db86e4b84b1f8ea0026d6a0f24fe09928c10334caba6ae58a605bb6b10caf
Frequently asked questions
How much VRAM does LongCat 2.0 require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support LongCat 2.0?
Certified upstream runtime evidence is available for sglang.
Can LongCat 2.0 be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official MIT License terms for the final obligations.
Official references
Last verified: 2026-08-26