Laguna-XS-2.1
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. This model is an upgraded version of our Laguna XS.2 model with a +5.4% jump on SWE-bench Multilingual as well as stronger performance on terminal-style tasks.
Params
33.4 B
Context
262,144
Downloads 30d
478 K
Likes
258
Download history
daily snapshots · 20 days478 K183 K
Oct 4Oct 10Oct 17Oct 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 | 66.9 GB | 79.1 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 66.9 GB | 234.6 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-xs-2-1
{
"hf_id": "poolside/Laguna-XS-2.1",
"params_b": 33.44,
"context_length": 262144,
"license": { "id": "openmdw-1.1", "commercial": "unknown" },
"downloads_30d": 477664,
"vram_estimates": [
{ "quant": "bf16", "gb": 79.1 }
],
"updated_at": "2026-10-04T01:00:18Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-23$0.06
input / 1M
$0.12
output / 1M
$0.03
cached input / 1M
$0.18
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 262,144 tokens
- Max output
- 32,768 tokens
- Providers
- 1
- Cheapest provider
- Poolside · $0.06 / $0.12
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✗ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- LagunaForCausalLM
- Parameters
- 33.4 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 100,352
- Layers / heads
- 40 / 48
- Licence
- openmdw-1.1
- First seen on the Hub
- 2026-06-20
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-04
Compare with any text-generation model
Popular comparisons
Appears in