- Context
- 262Ktokens
- Released
- 6mo ago
- Size
- 33.4Bparameters
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| laguna-xs.2:bf16 | — | — | BF16 | 67 GB | 128K | text |
| laguna-xs.2:mlx-bf16 | — | — | BF16 | 67 GB | 256K | text |
| laguna-xs.2:latest | — | — | Q4_K_M | 23 GB | 128K | text |
| laguna-xs.2:q8_0 | — | — | Q8_0 | 37 GB | 128K | text |
| laguna-xs.2:mxfp8 | — | — | — | 39 GB | 256K | text |
| laguna-xs.2:nvfp4 | — | — | — | 19 GB | 256K | text |
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.