Trinity-Large-Thinking
Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general ca...
Params
398.6 B
Context
262,144
Downloads 30d
2 K
Likes
190
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)2 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 | 797.3 GB | 937.3 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 797.3 GB | 2,791.0 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/trinity-large-thinking
{
"hf_id": "arcee-ai/Trinity-Large-Thinking",
"params_b": 398.64,
"context_length": 262144,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 2245,
"vram_estimates": [
{ "quant": "bf16", "gb": 937.3 }
],
"updated_at": "2026-10-19T06:00:04Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.25
input / 1M
$0.80
output / 1M
$0.06
cached input / 1M
$1.05
1M in + 1M out
- Context window
- 262,144 tokens
- Max output
- 80,000 tokens
- Providers
- 1
- Cheapest provider
- Arcee AI · $0.25 / $0.80
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 10.8 / 25.8 / 1
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- AfmoeForCausalLM
- Parameters
- 398.6 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 200,192
- Layers / heads
- 60 / 48
- Licence
- other
- First seen on the Hub
- 2026-04-01
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model