ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Meituan 美团 LongCat
Open-Weight Meituan 美团 LongCat · MoE 1.78T / A48B · Text · BF16 / FP8

Meituan LongCat-2.5 (1.78T MoE) Architecture Parameters, Benchmarks & VRAM

Meituan MIT-licensed 1.78T-parameter multimodal agentic MoE with 768 experts.

🧬 Meituan LongCat-2.5 (1.78T MoE) Architecture & Tensor Specifications

Verified directly against HuggingFace (meituan-longcat/LongCat-2.5) config.json & Model Card

HF Class: LongcatCausalLM

1. Backbone & Dimensions

pro_v
Total / Active Params
1.78T / 48B
Hidden Size (d_model)
8,192
MoE Experts
768 Routed
Activation / Norm
SiLU (SwiGLU) · ε=0.00001
Native Tensor Dtype
BF16 / FP8

2. Attention & Layer Layout

MLA
Num Hidden Layers
38 Layers
Hidden Layer Layout
38-Layer Sparse MoE (768 Experts)
Attention Heads (Q / KV)
64 Q / 8 KV (8:1 GQA)
Head Dimension
128

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
524,288 tokens
RoPE Configuration
RoPE (原生 524,288 Context)
Vocab Size
163,840 (Untied)

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Default Sampling
temperature=0.7 top_p=0.95 max_tokens=32,768

📊 Meituan LongCat-2.5 (1.78T MoE) Full Benchmark Scorecard

19 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 11 items

Terminal-Bench 2.1 #5/37 88.4%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

MCP Atlas #9/39 83.1%

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

PaperBench #1/3 82.1%

PaperBench is a benchmark for evaluating AI agents on their ability to replicate research papers. It tests models on complex, multi-step workflows involving code implementation, experimentation, and reproducing scientific results from academic publications.

Vision2Web #1/5 78.6%

Vision2Web evaluates multimodal models on converting visual designs and screenshots into functional web pages, measuring end-to-end design-to-code capability.

Claw-Eval #2/13 78.3%

Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.

DeepSWE 1.1 #29/49 64.6%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

SkillsBench #1/11 63.3%

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

NL2Repo #4/23 60.5%

NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.

SWE Atlas - Codebase QnA #3/5 58.3%

SWE Atlas - Codebase QnA evaluates a model's ability to answer questions about real codebases, measuring repository-level comprehension and the ability to reason about code structure, behavior, and intent across an entire project.

Terminal-Bench 4.0 #17/31 38.5%

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

Program Bench #14/18 25.5%

Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

⚡ Meituan LongCat-2.5 (1.78T MoE) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 1780B / A48B·38L (d=8192)·64Q/8KV·Ctx 1M
Runnable Models →
GPUs
96 GB VRAM·4000 GB/s·Safe Usable 94.1 GB
Out of VRAM (OOM)1101.87 / 94.1 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
1101.87/ 94.1 GB usable

Physical 96 GB · Load 1171.2%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 1007.79 GB

Max Context at Batch=1
0K/ 1M

MLA compresses multi-batch KV footprint

Weights: 1079.12 GBKV Cache (1×16K): 0.72 GBOverhead: 22.03 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run meituan-longcat-2-5

Insufficient Local VRAM? Ways to Run Meituan LongCat-2.5 (1.78T MoE)

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 Meituan LongCat-2.5 (1.78T MoE) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 3560 GB 0.72 GB 3632.37 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 1891.25 GB 0.72 GB 1930.24 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 1459.6 GB 0.72 GB 1489.96 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 1266.03 GB 0.72 GB 1292.51 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 1079.12 GB 0.72 GB 1101.87 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 945.63 GB 0.72 GB 965.7 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 869.98 GB 0.72 GB 888.54 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 700.88 GB 0.72 GB 716.06 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for Meituan LongCat-2.5 (1.78T MoE) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of Meituan LongCat-2.5 (1.78T MoE)?

Meituan LongCat-2.5 (1.78T MoE) uses LongcatCausalLM with 38 layers (38-Layer Sparse MoE (768 Experts)), hidden_size=8192, 64 Q heads / 8 KV heads (head_dim=128), and vocab_size=163,840.

How much VRAM does Meituan LongCat-2.5 (1.78T MoE) require?

At 4-bit quantization (Q4_K_M, 16K context), Meituan LongCat-2.5 (1.78T MoE) requires 1101.87 GB VRAM. Full FP16 requires 3632.37 GB.