Qwen3.6-35B-A3B-NVFP4 vs Laguna-XS-2.1
Specs, VRAM requirements and download trends — updated 23 October 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.2 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | Laguna-XS-2.1 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 18.7 B | 33.4 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LagunaForCausalLM |
| Context length | — | 262,144 |
| Licence | apache-2.0 | openmdw-1.1 |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 4,194,170 | 477,664 |
| Downloads all time | 39.3 M | 583 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2026-06-20 |
| API input price / 1M tokens | not on OpenRouter | $0.06 |
| API output price / 1M tokens | not on OpenRouter | $0.12 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.18 |
| Cached input / 1M tokens | not on OpenRouter | $0.03 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 32,768 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Laguna-XS-2.1
$0.18
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
12.6 M183 K
Qwen3.6-35B-A3B-NVFP4
Laguna-XS-2.1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
Laguna-XS-2.1 · fp16 @ 256K ctx
234.6 GB / 24 GB