Laguna-S-2.1
Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-wi...
Params
117.6 B
Context
1,048,576
Downloads 30d
397 K
Likes
1,060
Download history
daily snapshots · 18 days397 K190 K
Oct 6Oct 12Oct 18Oct 23
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 | 235.1 GB | 276.8 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 235.1 GB | 2,516.3 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/laguna-s-2-1
{
"hf_id": "poolside/Laguna-S-2.1",
"params_b": 117.56,
"context_length": 1048576,
"license": { "id": "openmdw-1.1", "commercial": "unknown" },
"downloads_30d": 397257,
"vram_estimates": [
{ "quant": "bf16", "gb": 276.8 }
],
"updated_at": "2026-10-06T01:00:18Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-23$0.09
input / 1M
$0.18
output / 1M
$0.009
cached input / 1M
$0.27
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Providers
- 1
- Cheapest provider
- Poolside · $0.09 / $0.18
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- LagunaForCausalLM
- Parameters
- 117.6 B
- Tensor type
- BF16
- Context length
- 1,048,576
- Vocabulary
- 100,352
- Layers / heads
- 48 / 48
- Licence
- openmdw-1.1
- First seen on the Hub
- 2026-07-13
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-06
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model
Popular comparisons
Appears in