Laguna-S-2.1-GGUF

Use on OpenRouter · Use on Vercel AI Gateway · Release blog post Laguna S 2.1 GGUF GGUF conversions of Laguna S 2.1 for llama.cpp, plus the DFlash speculative-decoding draft model. See the base model card for architecture details, license, and usage guidance. Files | File | Size | Notes | |------|------|-------| | `laguna-s-2.1-F16.gguf` | 235 GB | full precision | | `laguna-s-2.1-Q8_0.gguf` | 128 GB | | | `laguna-s-2.1-Q4_K_M.gguf` | 75 GB | imatrix-quantized | | `laguna-s-2.1-DFlash-BF16.gguf` | 2.2 GB | DFlash drafter for speculative decoding | | `laguna-s-2.1.imatrix` | 0.4 GB | importance matrix used for the K-quants | Serving Serve with Poolside's llama.cpp fork, branch `laguna`, which carries full Laguna support including DFlash speculative decoding. (Base Laguna support is also in upstream review: ggml-org/llama.cpp#25165.) Context length These GGUFs ship configured for a 262,144-token (256K) context window. This is the configuration we recommend for best output quality. The weights are native 1M checkpoints: training included a long-context extension stage up to 1,048,576 tokens. To use more than 256K of context with llama.cpp, override the rope configuration at load time: You may experience quality degradation with the 1M configuration. If you use it, we recommend sampling with `--temp 0.7 --top-p 0.95`. This release also corrects the embedded `yarn_attn_factor` metadata (now 1.0; llama.cpp derives the YaRN attention scaling internally).