Ripple-65B-Preview
Ricursive Intelligence introduces Ripple-65B Preview, a 65B parameter dense Transformer model pretrained on 12 trillion tokens with support for up to 1Mi (1,048,576 tokens) of context. Ripple-65B Preview delivers strong results on agentic coding, scoring 80.52 on TerminalBench 2.1 and surpassing significantly-larger US open-weight models such as Reflection Beam 501B (80.1), Meta Muse Spark Open 816B (76.4), Thinking...
Params
64.8 B
Context
2,097,152
Downloads 30d
6 K
Likes
458
Download history
tracking started — chart appears after 7 days of snapshots (0 recorded)6 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 | 129.6 GB | 152.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 2048K ctx | 129.6 GB | 2,630.7 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/ripple-65b-preview-ricursiveai
{
"hf_id": "ricursiveAI/Ripple-65B-Preview",
"params_b": 64.78,
"context_length": 2097152,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 5835,
"vram_estimates": [
{ "quant": "bf16", "gb": 152.7 }
],
"updated_at": "2026-11-10T06:00:04Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.20
input / 1M
$0.60
output / 1M
$0.05
cached input / 1M
$0.80
1M in + 1M out
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Providers
- 3
- Cheapest provider
- PrimeIntellect · $0.10 / $0.30
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- RicursiveForCausalLM
- Parameters
- 64.8 B
- Tensor type
- BF16
- Context length
- 2,097,152
- Vocabulary
- 100,352
- Layers / heads
- 80 / 80
- Licence
- apache-2.0
- First seen on the Hub
- 2026-11-04
- Training datasets
- undisclosed
Compare with any text-generation model