LongCat-2.0
We introduce LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token — a substantial step up from previous LongCat models, accompanied by several architectural improvements.
Params
1,775.6 B
Context
262,144
Downloads 30d
3 K
Likes
282
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)3 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 3,551.7 GB | 4,173.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 3,551.7 GB | 12,430.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/longcat-2-0
{
"hf_id": "meituan-longcat/LongCat-2.0",
"params_b": 1775.56,
"context_length": 262144,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 2563,
"vram_estimates": [
{ "quant": "bf16", "gb": 4173.7 }
],
"updated_at": "2026-10-19T06:02:43Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.30
input / 1M
$1.20
output / 1M
$0.006
cached input / 1M
$1.50
1M in + 1M out
- Context window
- 1,048,756 tokens
- Max output
- 262,144 tokens
- Providers
- 1
- Cheapest provider
- AtlasCloud · $0.30 / $1.20
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 19.1 / 45.3 / 14
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- LongcatCausalLM
- Parameters
- 1,775.6 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 163,840
- Licence
- mit
- First seen on the Hub
- 2026-07-05
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model