// Meituan LongCat · Text LLM
LongCat-Flash-Lite: VRAM & local deployment
68.5B total · 3B active (MoE) parameters. About 46.3 GB at 4-bit and 151 GB at BF16 with one 8K-token request.
released 2026-01-27licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Meituan · meituan-longcat |
|---|---|
| Family / series | Meituan LongCat · LongCat-Flash-Lite |
| Type | Text LLM (text-generation) |
| Parameters | 68.5B total · 3B active (MoE) Source: official model card“68.5B parameter MoE model with approximately 3B activated parameters” |
| Context length | 320K tokens (327,680)max_position_embeddings in config.json |
| Architecture | 14 layers · MLA · MoE |
| Released weights | BF16 · 138 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2026-01-27 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 137 GB | 151 GB | 152 GB | 153 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB |
| FP8 / INT8 / Q8_0 | 72.8 GB | 80.7 GB | 81.1 GB | 82.7 GB | RTX PRO 6000 96GB | Mac 128GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 41.5 GB | 46.3 GB | 46.7 GB | 48.3 GB | 2 × RTX 5090 (64GB) | Mac 128GB |
KV cache per request: 8K 0.1 GB · 32K 0.5 GB · 128K 2.1 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- SGLang — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from meituan-longcat.
05Other Meituan LongCat models
All 16 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| LongCat-Flash-Lite-Sparse | 69B / 3B | 46.6 GB | 2026-07-31 |
| LongCat-2.0 | 1.6T / 48B | 1.07 TB | 2026-07-05 |
| LongCat-AudioDiT-1B | 1.42B | 1.4 GB | 2026-03-30 |
| LongCat-AudioDiT-3.5B | 3.83B | 3.1 GB | 2026-03-30 |
| LongCat-Image-Edit-Turbo | — | — | 2026-02-03 |
| LongCat-Flash-Thinking-ZigZag | 561.9B | 376 GB | 2026-01-23 |
| LongCat-Flash-Thinking-2601 | 560B / 27B | 374 GB | 2026-01-14 |
| LongCat-HeavyMode-Summary | 561.9B | 376 GB | 2026-01-14 |
06Sources
Data checked 2026-02-06. Parameters, context and licence are copied from the official repository; memory figures are our estimates.