Skip to content
English

Switch theme

// Meituan LongCat · Text LLM

LongCat-2.0: VRAM & local deployment

1.6T total · 48B active (MoE) parameters. About 1.07 TB at 4-bit and 3.52 TB at BF16 with one 8K-token request.

released 2026-07-05licence: Commercial OKmemory figures are estimates

01Specs

PublisherMeituan · meituan-longcat
Family / seriesMeituan LongCat · LongCat-2.0
TypeText LLM (text-generation)
Parameters1.6T total · 48B active (MoE) Source: official model card“1.6 trillion total parameters and ~48 billion activated per token”
Context length256K tokens (262,144)max_position_embeddings in config.json
Architecture38 layers · MLA · MoE
Released weightsBF16 · 3.55 TBdownload
LicenceMIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-07-05 (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.

PrecisionWeightsTotal @ 8KTotal @ 32KTotal @ 128KSmallest GPUMac
BF16 / FP16 (original)3.20 TB 3.52 TB3.52 TB3.53 TB 2 × 8 × B300 nodes (4,608GB)—
FP8 / INT8 / Q8_01.70 TB 1.87 TB1.87 TB1.88 TB 8 × B300 (2,304GB)—
4-bit (Q4_K_M / AWQ / GPTQ-Int4)970 GB 1.07 TB1.07 TB1.07 TB 8 × B200 (1,440GB)—

KV cache per request: 8K 0.4 GB · 32K 1.4 GB · 128K 5.7 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.

Which inference engine to choose →

04Official repositories & quantised builds

3 official repo(s) from meituan-longcat.

05Other Meituan LongCat models

All 16 →
ModelParams4-bit totalReleased
LongCat-Flash-Lite-Sparse69B / 3B46.6 GB2026-07-31
LongCat-AudioDiT-1B1.42B1.4 GB2026-03-30
LongCat-AudioDiT-3.5B3.83B3.1 GB2026-03-30
LongCat-Image-Edit-Turbo——2026-02-03
LongCat-Flash-Lite68.5B / 3B46.3 GB2026-01-27
LongCat-Flash-Thinking-ZigZag561.9B376 GB2026-01-23
LongCat-Flash-Thinking-2601560B / 27B374 GB2026-01-14
LongCat-HeavyMode-Summary561.9B376 GB2026-01-14

06Sources

Data checked 2026-07-08. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)