Downloads · 30 days
32
11% of all-time downloads
peasantsmith/Laguna-S-2.1-PS-IQ2_XXS-GGUF
Laguna-S-2.1-PS-IQ2_XXS-GGUF is a text generation model from peasantsmith. Use it when you need the model to write or continue text. It is set up for gguf.
Compact GGUF quantization of Laguna-S-2.1, released by PeasantSmith. Inspired by Antirez's mixed-precision GGUF work.
Downloads · 30 days
32
11% of all-time downloads
All-time downloads
300
Public
Repo size
33.7 GB
Likes
2
Public
Click a slice to open those files.
.gguf33.7 GB · 100%
From the Hugging Face model README
Compact GGUF quantization of Laguna-S-2.1, released by PeasantSmith. Inspired by Antirez's mixed-precision GGUF work.
MoE, 118B total / 8B active params: 256 routed experts + 1 shared, top-10 routing, 48 layers (12 global attention + 36 sliding-window, window 512), GQA. Context up to 1,048,576 tokens via YaRN scaling on the global layers. Built for agentic coding and long-horizon tasks.
| Model | PPL |
|---|---|
| Laguna-S-2.1 F16 reference | 9.50 |
| Laguna-S-2.1 PS-IQ2_XXS | 11.5095 ± 0.26229 |
PPL was measured with llama-perplexity on the evaluation corpus. Results are corpus-dependent.
temperature: 1.0
top_k: 20
top_p: 1.0
Compatible with GGUF runtimes including llama.cpp and Ollama.
OpenMDW-1.1, inherited from the base model.
Independently produced, experimental release with limited compute for testing. Feedback on quality, stability, and cross-runtime compatibility is welcome. See the upstream model page for full docs and license terms; verify behavior for your workload before relying on this in production.