Laguna S 2.1 is a poolside ~118B total / ~8B active per token Mixture-of-Experts model for agentic coding and long-horizon work. Architecture highlights: token-choice routing with softplus gates, 256 routed experts + 1 shared expert (top-10), GQA, 1:3 global/sliding-window attention (48 layers: 12 global + 36 local, window 512), and up to about 1M context, with optional native thinking interleaved with tool use.

This release builds on the official weights in two steps:

1. Uncensored behavior edit via abliterix (ROCm + bitsandbytes 4-bit search path), selecting Trial 16 LoRA, stream-merged back to BF16, plus MoE safety-expert router bake-in.
2. APEX mixed-precision GGUF quantized from the BF16 GGUF of our Laguna-S-2.1-Uncensored (converted with poolside llama.cpp (laguna)), using APEX-style tensor-type configs + imatrix (token embedding / output kept at BF16).

License: OpenMDW-1.1 (same family as the base model). See openmdw.ai and poolside terms.

After merging abliterix Trial 16, this model shows a much lower refusal rate and can differ substantially from official Laguna-S-2.1. Evaluate compliance and safety for your use case; control access and audit as needed.

Implementation sketch: LoRA merge W += (B @ A) * (alpha / r) (this trial alpha = r = 1); per-layer top ~20 safety experts with router row scale ~0.74 (see merge metadata).

The following can also appear with official Laguna-S-2.1 (including high-precision online deployments). They are not introduced by this Uncensored edit and should not be blamed on abliterix / the refusal merge:

• Model identity quirks or self-descriptions that diverge from the official persona;
• Odd tokens, typos, stiffness, or occasional awkward phrasing in Chinese and other languages.

This Uncensored pipeline mainly changes refusal / safety-related behavior. More aggressive quant tiers (e.g. Compact / Mini) may amplify existing text noise, but the underlying issues already exist in the original model and/or the local quant+inference stack. For a fair check, compare official vs this release under the same serving settings.

Coding / tool ability is largely retained; refusal and alignment behavior are changed. Full official bench tables were not re-run for this derivative.

These files use APEX-style MoE-aware mixed precision: precision follows tensor role + layer position (higher on edges, more aggressive in the middle), with imatrix for the I- tiers.

Common settings for this package: source Laguna-S-2.1-Uncensored BF16 GGUF; calibration laguna-s-2.1.imatrix; token embedding / output = BF16; routers and norms largely left at high precision defaults. Configs target Laguna 48-layer naming (ffn_*_exps / ffn_*_shexp / attn_*, L0 dense).

How to choose:

• Chinese-heavy use: prefer I-Balanced. Mid experts stay Q5_K (not IQ), which usually feels more stable. Drop to I-Compact if memory is tight; use I-Mini only when you need the smallest footprint and accept more noise.
• English / coding: tier differences are usually smaller; pick by VRAM/speed (Balanced → Compact → Mini). I-Quality is optional when you want IQ mid-layers and a smaller footprint than Balanced.
• I-Mini: ~41 GB, mid experts at iq2_s (requires imatrix). Good for 128 GB unified-memory boxes with room for long context, or machines that cannot hold Compact. Expect more quant artifacts than Compact.

Use a build that understands the laguna architecture (poolside laguna branch or equivalent).

Example (I-Balanced recommended)

./llama-server \
  -m ./Laguna-S-2.1-Uncensored-APEX-I-Balanced.gguf \
  --port 8080 \
  -sm none \
  --device rocm0 \
  --ctx-size 131072 \
  --flash-attn on \
  --no-mmap \
  --fit on \
  --jinja \
  --host 0.0.0.0

• Must recognize general.architecture = laguna.
• Thinking / tools: configure per client/server docs (e.g. enable_thinking, reasoning options).
• Warnings like special_eos_id is not in special_eog_ids are tokenizer metadata hints; the model can still load. If stop/truncation is odd, check stop / max_tokens / template.
• Text-only GGUF; no mmproj.

1. Base: poolside/Laguna-S-2.1
2. abliterix search → Trial 16 LoRA + MoE router adjustments
3. BF16 stream-merge → Laguna-S-2.1-Uncensored
4. poolside llama.cpp → BF16 GGUF + imatrix
5. APEX tensor-type-file + imatrix → I-Quality / I-Balanced / I-Compact / I-Mini