- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- meituan-longcat
- Family
- LongCat
- Task
- text-generation
- Hugging Face
- meituan-longcat/LongCat-2.0
- OpenRouter
- meituan/longcat-2.0
- Also known as
- LongCat 2.0, longcat-2.0, meituan longcat
02Registry facts
- LicenceFACT
mit
- FreshRetrieved 19 Sep 2026
- ParametersFACT
1775.6B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
1,672
- FreshRetrieved 19 Sep 2026
- LikesFACT
270
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
1672
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · AtlasCloudFACT
1048756
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
270
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
mit
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
1775560491136
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · AtlasCloudFACT
1.2000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · AtlasCloudFACT
0.3000
- AgeingRetrieved 19 Sep 2026
Other
- last modifiedFACT
2026-07-08T06:29:21.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
LongCat-2.0
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 1775.6B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 3551.12 GB | 4101.08 GB |
| fp8 | 1775.56 GB | 2059.18 GB |
| int4 | 887.78 GB | 1038.23 GB |
What this estimate assumes
- Weights: 1775.6B parameters × 2 bytes per parameter (fp16) = 3551.12 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 534.92 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.3
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
1.2
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| AtlasCloud | 1,048,756 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01–03Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — meituan/longcat-2.0
https://openrouter.ai/api/v1/models/meituan/longcat-2.0/endpoints
AgeingRetrieved 19 Sep 2026sha256:a1d9fd6a52a13 records · ·
- 04–10Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — meituan-longcat/LongCat-2.0
https://huggingface.co/api/models/meituan-longcat/LongCat-2.0
AgeingRetrieved 19 Sep 2026sha256:e158623265437 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.