Laguna-S-2.1-Uncensored-APEX-GGUF

<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; margin-bottom: 24px;"> <div style="background: #f5f5f7; border-radius: 20px; padding: 36px 32px; margin-bottom: 20px; text-align: center; position: relative; overflow: hidden;"> <div style="position: absolute; top: -30px; right: -30px; width: 120px; height: 120px; background: #ddd6fe; border-radius: 50%;"></div> <div style="position: absolute; bottom: -20px; left: 40px; width: 80px; height: 80px; background: #c4b5fd; border-radius: 50%;"></div> <div style="position: absolute; top: 50%; left: -15px; width: 60px; height: 60px; background: #ddd6fe; border-radius: 50%;"></div> <div style="display: inline-flex; gap: 8px; margin-bottom: 16px; position: relative; z-index: 1; flex-wrap: wrap; justify-content: center;"> <span style="background: #6366f1; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">ABLITERIX</span> <span style="background: #8b5cf6; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">TRIAL 16</span> <span style="background: #0ea5e9; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">APEX</span> <span style="background: #64748b; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">OpenMDW-1.1</span> </div> <h1 style="margin: 0 0 8px 0; font-size: 28px; font-weight: 700; color: #1e1b4b; letter-spacing: -0.5px; border: none; position: relative; z-index: 1;">Laguna-S-2.1-Uncensored-APEX-GGUF</h1> <p style="margin: 8px 0 0 0; font-size: 14px; position: relative; z-index: 1;"><span style="color: #6b7280;">English</span> | <a href="https://huggingface.co/SC117/Laguna-S-2.1-Uncensored-APEX-GGUF/blob/main/README_zh.md" style="color: #6366f1; text-decoration: none;">📖 中文文档</a></p> <p style="margin: 8px 0 0 0; font-size: 15px; color: #6b7280; position: relative; z-index: 1;">Uncensored 118B-A8B MoE · abliterix Trial 16 · APEX I-tier GGUFs + imatrix</p> </div> </div> <div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; display: flex; flex-direction: column; gap: 20px; margin-bottom: 30px;"> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🌊</span> About this release</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;"><a href="https://huggingface.co/poolside/Laguna-S-2.1" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">Laguna S 2.1</a> is a poolside <b>~118B total / ~8B active per token</b> Mixture-of-Experts model for agentic coding and long-horizon work. Architecture highlights: token-choice routing with softplus gates, <b>256 routed experts + 1 shared expert (top-10)</b>, GQA, <b>1:3 global/sliding-window attention</b> (48 layers: 12 global + 36 local, window 512), and up to about <b>1M context</b>, with optional native thinking interleaved with tool use.</p> <p style="margin: 0 0 12px 0;">This release builds on the official weights in two steps:</p> <ol style="margin: 0 0 12px 0; padding-left: 20px;"> <li style="margin-bottom: 6px;"><b>Uncensored behavior edit</b> via <a href="https://github.com/wuwangzhang1216/abliterix" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">abliterix</a> (ROCm + bitsandbytes 4-bit search path), selecting <b>Trial 16</b> LoRA, stream-merged back to BF16, plus MoE safety-expert router bake-in.</li> <li style="margin-bottom: 6px;"><b>APEX mixed-precision GGUF</b> quantized from the BF16 GGUF of our <a href="https://huggingface.co/SC117/Laguna-S-2.1-Uncensored" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">Laguna-S-2.1-Uncensored</a> (converted with poolside <a href="https://github.com/poolsideai/llama.cpp/tree/laguna" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">llama.cpp (laguna)</a>), using <a href="https://github.com/mudler/apex-quant" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">APEX</a>-style tensor-type configs + <b>imatrix</b> (token embedding / output kept at <b>BF16</b>).</li> </ol> <p style="margin: 0;"><b>License: OpenMDW-1.1</b> (same family as the base model). See <a href="https://openmdw.ai/" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">openmdw.ai</a> and poolside terms.</p> </div> </div> <div style="border: 1px solid #fdba74; border-radius: 12px; overflow: hidden; background: #fff7ed; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #f97316 0%, #ea580c 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>⚠️</span> Uncensored notice</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;">After merging abliterix <b>Trial 16</b>, this model shows a <b>much lower refusal rate</b> and can differ substantially from official Laguna-S-2.1. Evaluate compliance and safety for your use case; control access and audit as needed.</p> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Refusals (harmful eval)</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;"><b>8 / 100</b> (baseline ~97 / 100)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">KL divergence</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">~0.0042</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Length deviation</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">~0.07 σ</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Generation health</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">PASSED</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">Selected trial</td><td style="padding: 6px 10px; color: #4b5563; background: white;">abliterix Trial 16</td></tr> </tbody></table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #9a3412;">Implementation sketch: LoRA merge <code>W += (B @ A) * (alpha / r)</code> (this trial alpha = r = 1); per-layer top ~20 safety experts with router row scale ~0.74 (see merge metadata).</p> </div> </div> <div style="border: 1px solid #c4b5fd; border-radius: 12px; overflow: hidden; background: #f5f3ff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #7c3aed 0%, #6d28d9 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📜</span> Disclaimer (identity &amp; text quality)</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;">The following can also appear with <b>official Laguna-S-2.1</b> (including high-precision online deployments). They are <b>not introduced by this Uncensored edit</b> and should not be blamed on abliterix / the refusal merge:</p> <ul style="margin: 0 0 12px 0; padding-left: 20px;"> <li style="margin-bottom: 6px;"><b>Model identity</b> quirks or self-descriptions that diverge from the official persona;</li> <li style="margin-bottom: 6px;">Odd tokens, typos, stiffness, or occasional awkward phrasing in Chinese and other languages.</li> </ul> <p style="margin: 0;">This Uncensored pipeline mainly changes <b>refusal / safety-related behavior</b>. More aggressive quant tiers (e.g. Compact / Mini) may <b>amplify</b> 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.</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🧠</span> Model details</div> <div style="padding: 16px;"> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Architecture</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Laguna MoE (poolside <code>laguna</code>)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Parameters</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">~118B total, ~8B active / token</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Layers</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">48 (L0 dense FFN, L1–L47 MoE)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Experts</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">256 routed + 1 shared, top-10</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Attention</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">GQA, 8 KV heads, head dim 128</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Context</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Up to ~1,048,576 tokens (practical limit depends on VRAM / <code>-c</code>)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Vocab</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">100,352 (Laguna family tokenizer)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Modality</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Text → text (no mmproj in this package)</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">This repo</td><td style="padding: 6px 10px; color: #4b5563; background: white;">APEX I-Quality / I-Balanced / I-Compact / I-Mini GGUF</td></tr> </tbody></table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b;">Coding / tool ability is largely retained; refusal and alignment behavior are changed. Full official bench tables were not re-run for this derivative.</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>💡</span> What is APEX?</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;">These files use <a href="https://github.com/mudler/apex-quant" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">APEX</a>-style MoE-aware mixed precision: precision follows <b>tensor role + layer position</b> (higher on edges, more aggressive in the middle), with <b>imatrix</b> for the <code>I-</code> tiers.</p> <p style="margin: 0;">Common settings for this package: source <code>Laguna-S-2.1-Uncensored</code> BF16 GGUF; calibration <code>laguna-s-2.1.imatrix</code>; <b>token embedding / output = BF16</b>; routers and norms largely left at high precision defaults. Configs target Laguna 48-layer naming (<code>ffn_*_exps</code> / <code>ffn_*_shexp</code> / <code>attn_*</code>, L0 dense).</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📦</span> APEX quantization tiers</div> <div style="padding: 16px;"> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><thead><tr style="background: rgba(99,102,241,0.06);"> <th style="padding: 8px 10px; border-bottom: 2px solid #6366f1; text-align: left; color: #4f46e5;">File</th> <th style="padding: 8px 10px; border-bottom: 2px solid #6366f1; text-align: left; color: #4f46e5;">Size</th> <th style="padding: 8px 10px; border-bottom: 2px solid #6366f1; text-align: left; color: #4f46e5;">Mid experts</th> <th style="padding: 8px 10px; border-bottom: 2px solid #6366f1; text-align: left; color: #4f46e5;">Best for</th> </tr></thead><tbody> <tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;"><code>*-I-Quality.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">~70 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">edge Q6_K / near Q5_K / mid <b>iq4_xs</b>; shared Q8_0; attn Q6_K</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">Smaller high-quality try (IQ mid-layers)</td></tr> <tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: #eef2ff;"><code>*-I-Balanced.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: #eef2ff;"><b>~80 GB</b></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: #eef2ff;">edge Q6_K / near &amp; mid <b>Q5_K</b>; shared Q8_0; attn Q6_K</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: #eef2ff;"><b>Recommended default for Chinese users</b> — steadier than Compact / Mini</td></tr> <tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;"><code>*-I-Compact.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">~52 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">edge Q4_K / mid Q3_K; shared Q6_K; attn Q4_K</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); background: white;">Tighter memory; more quant noise OK</td></tr> <tr><td style="padding: 8px 10px; background: white;"><code>*-I-Mini.gguf</code></td><td style="padding: 8px 10px; background: white;">~41 GB</td><td style="padding: 8px 10px; background: white;">edge Q3_K / near Q3_K / mid <b>iq2_s</b>; shared Q5_K→Q4_K; attn Q4_K / Q3_K</td><td style="padding: 8px 10px; background: white;">Smallest I-tier here; fits ~48–64 GB unified / VRAM budgets; highest quant noise</td></tr> </tbody></table> <p style="margin: 12px 0 0 0; font-size: 13px; color: #334155; line-height: 1.7;"><b>How to choose:</b></p> <ul style="margin: 8px 0 0 0; padding-left: 20px; font-size: 13px; color: #334155; line-height: 1.7;"> <li style="margin-bottom: 6px;"><b>Chinese-heavy use:</b> prefer <b>I-Balanced</b>. Mid experts stay Q5_K (not IQ), which usually feels more stable. Drop to I-Compact if memory is tight; use <b>I-Mini</b> only when you need the smallest footprint and accept more noise.</li> <li style="margin-bottom: 6px;"><b>English / coding:</b> 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.</li> <li style="margin-bottom: 0;"><b>I-Mini:</b> ~41 GB, mid experts at <b>iq2_s</b> (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.</li> </ul> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🚀</span> Usage (llama.cpp)</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 8px 0;">Use a build that understands the <b>laguna</b> architecture (poolside <code>laguna</code> branch or equivalent).</p> <p style="margin: 0 0 8px 0; font-weight: bold; color: #312e81;">Example (I-Balanced recommended)</p> <pre style="margin: 0 0 12px 0; font-family: monospace; background: #f8fafc; padding: 10px 14px; border-radius: 6px; border: 1px solid #e2e8f0; font-size: 12px; color: #1e293b; white-space: pre-wrap;">./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</pre> <ul style="margin: 0; padding-left: 20px;"> <li style="margin-bottom: 6px;">Must recognize <code>general.architecture = laguna</code>.</li> <li style="margin-bottom: 6px;">Thinking / tools: configure per client/server docs (e.g. <code>enable_thinking</code>, reasoning options).</li> <li style="margin-bottom: 6px;">Warnings like <code>special_eos_id is not in special_eog_ids</code> are tokenizer metadata hints; the model can still load. If stop/truncation is odd, check stop / max_tokens / template.</li> <li style="margin-bottom: 0;">Text-only GGUF; no mmproj.</li> </ul> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🎛️</span> Recommended sampling</div> <div style="padding: 16px;"> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">General / coding</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white; font-family: monospace;">temperature 0.6–1.0, top_p 0.95, top_k 20</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">More stable</td><td style="padding: 6px 10px; color: #4b5563; background: white;">Slightly lower temperature</td></tr> </tbody></table> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🔧</span> Build pipeline (summary)</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <ol style="margin: 0; padding-left: 20px;"> <li style="margin-bottom: 6px;">Base: <code>poolside/Laguna-S-2.1</code></li> <li style="margin-bottom: 6px;">abliterix search → <b>Trial 16</b> LoRA + MoE router adjustments</li> <li style="margin-bottom: 6px;">BF16 stream-merge → <code>Laguna-S-2.1-Uncensored</code></li> <li style="margin-bottom: 6px;">poolside llama.cpp → BF16 GGUF + imatrix</li> <li style="margin-bottom: 0;">APEX tensor-type-file + imatrix → I-Quality / I-Balanced / I-Compact / I-Mini</li> </ol> </div> </div> </div>

Links

• Original model: https://huggingface.co/poolside/Laguna-S-2.1
• Announcement: https://poolside.ai/blog/introducing-laguna-s-2-1
• OpenRouter: https://openrouter.ai/poolside/laguna-s-2.1
• Official GGUF: https://huggingface.co/poolside/Laguna-S-2.1-GGUF
• poolside llama.cpp (laguna): https://github.com/poolsideai/llama.cpp/tree/laguna
• abliterix: https://github.com/wuwangzhang1216/abliterix
• APEX: https://github.com/mudler/apex-quant
• License: https://openmdw.ai/

Disclaimer

Community derivative (behavior edit + quantization). Not an official poolside release. Use at your own risk; follow local law and upstream licenses.

<!-- SC117_SUPPORT_START --> <div align="center"> <a href="https://ko-fi.com/sc117"> <img src="https://huggingface.co/SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF/resolve/main/assets/support-sc117.png" alt="Support SC117 on Ko-fi — support is optional and all releases remain freely available." width="100%" /> </a> </div> <!-- SC117_SUPPORT_END -->