SC117/Qwen3.5-122B-A10B-Uncensored-APEX-Compact-GGUF

<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: 16px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 8px rgba(0,0,0,0.04);"> <div style="background: linear-gradient(135deg, #f59e0b 0%, #d97706 100%); padding: 28px 24px; color: white; text-align: center; position: relative; overflow: hidden;"> <div style="position: absolute; top: -30px; right: -30px; width: 120px; height: 120px; background: rgba(255,255,255,0.1); border-radius: 50%;"></div> <div style="position: absolute; bottom: -20px; left: 40px; width: 80px; height: 80px; background: rgba(255,255,255,0.08); border-radius: 50%;"></div> <h1 style="margin: 0; font-size: 24px; font-weight: 700; position: relative; z-index: 1;">⚡ Qwen3.5-122B-A10B Uncensored — APEX I-Compact GGUF</h1> <p style="margin: 8px 0 0 0; font-size: 14px; position: relative; z-index: 1;"> <span style="color: #86868b;">English</span> | <a href="https://huggingface.co/SC117/Qwen3.5-122B-A10B-Uncensored-APEX-Compact-GGUF/blob/main/READMEzh.md" style="color: #007aff; text-decoration: none;">📖 中文文档</a></p> <p style="margin: 8px 0 0 0; font-size: 15px; opacity: 0.95; position: relative; z-index: 1;">MoE Mixed-Precision Quantization · Uncensored · 55.1 GB</p> </div> <div style="padding: 16px 24px; background: #f8fafc; border-bottom: 1px solid #e2e8f0; display: flex; flex-wrap: wrap; gap: 8px;"> <span style="background: #fef3c7; color: #92400e; padding: 4px 12px; border-radius: 20px; font-size: 12px; font-weight: 600;">APEX I-Compact</span> <span style="background: #dbeafe; color: #1e40af; padding: 4px 12px; border-radius: 20px; font-size: 12px; font-weight: 600;">MoE 122B</span> <span style="background: #fce7f3; color: #9d174d; padding: 4px 12px; border-radius: 20px; font-size: 12px; font-weight: 600;">Uncensored</span> <span style="background: #d1fae5; color: #065f46; padding: 4px 12px; border-radius: 20px; font-size: 12px; font-weight: 600;">55.1 GB</span> <span style="background: #ede9fe; color: #5b21b6; padding: 4px 12px; border-radius: 20px; font-size: 12px; font-weight: 600;">Multimodal</span> </div> <div style="padding: 20px 24px;"> <p style="margin: 0; font-size: 14px; color: #334155; line-height: 1.7;"> <b>Qwen3.5-122B-A10B</b> (uncensored by <a href="https://huggingface.co/HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive" style="color: #c2410c; text-decoration: none;">HauhauCS</a>) quantized with <b>APEX I-Compact</b> — a MoE-aware mixed-precision strategy that applies layer-wise precision gradients. Edge layers get higher precision, middle layers get aggressive compression. Quantized from Q8KP using the <a href="https://github.com/mudler/apex-quant" style="color: #c2410c; text-decoration: none;">APEX project</a>. </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, #f59e0b 0%, #d97706 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>📊</span> Benchmark Results </div> <div style="padding: 16px;"> <p style="margin: 0 0 12px 0; font-size: 13px; color: #64748b; line-height: 1.5;">Measurements from APEX project on 8×RTX PRO 6000 Blackwell (768 GB VRAM). Perplexity on wikitext-2-raw (ctx 512). Accuracy via llama.cpp (400 tasks each).</p> <table style="width: 100%; border-collapse: collapse; font-family: inherit; font-size: 13px;"> <thead> <tr style="background: rgba(245, 158, 11, 0.05);"> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: left; color: #92400e; font-weight: bold;">Profile</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">Size</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">PPL</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">HellaSwag</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">Wino</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">MMLU</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">ARC</th> <th style="padding: 8px 10px; border-bottom: 2px solid #f59e0b; text-align: right; color: #92400e; font-weight: bold;">t/s</th> </tr> </thead> <tbody> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Q80 (ref)</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">121 GB</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">4.819</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">85.5%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">77.3%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">44.19</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">57.19</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">85.5</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">APEX I-Balanced</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">83.4 GB</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">4.831</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">85.5%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">77.8%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">43.86</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">57.86</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">96.7</td></tr> <tr style="background: rgba(245, 158, 11, 0.04);"><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold;">APEX I-Compact ★</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">55.1 GB</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">4.978</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">84.5%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">77.5%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">44.06</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">57.86</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #92400e; font-weight: bold; text-align: right;">106.3</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">APEX I-Mini</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">44.9 GB</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">5.306</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">84.0%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">75.3%</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">42.83</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">56.52</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: right;">110.0</td></tr> </tbody> </table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; line-height: 1.5;">★ <b>This quantization</b>. I-Compact achieves 84.5% HellaSwag and 57.86 ARC at <b>55% less size than Q80</b>, fastest standard APEX profile at 106 t/s. Quantized from Q8KP (137 GB → 55.1 GB).</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, #2563eb 0%, #1d4ed8 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>🔬</span> Quantization Strategy </div> <div style="padding: 16px;"> <p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7;"> APEX I-Compact applies <b>layer-wise mixed-precision</b> with MoE-aware tensor classification. Edge layers (L0–4, L43–47) get higher precision, middle layers (L10–29) get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces) for better real-world accuracy. </p> <table style="width: 100%; border-collapse: collapse; font-family: inherit; font-size: 13px;"> <thead> <tr style="background: rgba(37, 99, 235, 0.05);"> <th style="padding: 8px 10px; border-bottom: 2px solid #2563eb; text-align: left; color: #1d4ed8; font-weight: bold;">Component</th> <th style="padding: 8px 10px; border-bottom: 2px solid #2563eb; text-align: center; color: #1d4ed8; font-weight: bold;">Edge (L0-4, L43-47)</th> <th style="padding: 8px 10px; border-bottom: 2px solid #2563eb; text-align: center; color: #1d4ed8; font-weight: bold;">Middle (L10-29)</th> <th style="padding: 8px 10px; border-bottom: 2px solid #2563eb; text-align: center; color: #1d4ed8; font-weight: bold;">Role</th> </tr> </thead> <tbody> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Routed Experts (exps)</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q3KM</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q3KS</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #64748b; text-align: center;">256 experts, 8 active</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Shared Experts (shexp)</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q4KS</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q4KS</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #64748b; text-align: center;">Always active</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Attention (QKV)</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q4KS</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">Q3KM</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #64748b; text-align: center;">Per-layer attention</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Router (gateinp)</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">F32</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; text-align: center;">F32</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #64748b; text-align: center;">Precision-critical</td></tr> </tbody> </table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; line-height: 1.5;">Router weights kept in F32 (lossless) to preserve routing accuracy. Shared experts at Q4KS across all layers for stable token processing.</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, #059669 0%, #10b981 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>🏗️</span> Architecture </div> <div style="padding: 16px;"> <table style="width: 100%; border-collapse: collapse; font-family: inherit; font-size: 13px;"> <tbody> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600; width: 40%;">Base Model</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;"><a href="https://huggingface.co/HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive" style="color: #c2410c; text-decoration: none;">HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive</a></td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Parameters</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">122B total, ~10B active per token</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Experts</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">256 routed + 1 shared (8 active per token)</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Architecture</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Hybrid: Gated DeltaNet linear attention + softmax attention (3:1)</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Layers</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">48 (12 × (3 DeltaNet-MoE + 1 Attention-MoE))</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Context</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">262K native</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Modalities</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Text, Image, Video (natively multimodal)</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Vocabulary</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">248K tokens, 201 languages</td></tr> <tr><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #047857; font-weight: 600;">Uncensored</td><td style="padding: 8px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155;">Aggressive variant — 0/465 refusals</td></tr> <tr><td style="padding: 8px 10px; color: #047857; font-weight: 600;">Quantized From</td><td style="padding: 8px 10px; color: #334155;">Q8KP (137 GB → 55.1 GB, 3.88 BPW effective)</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, #ea580c 0%, #f97316 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>⚙️</span> Recommended Settings </div> <div style="padding: 16px;"> <p style="margin: 0 0 8px 0; font-size: 13px; color: #334155; line-height: 1.7;"><b>Thinking mode (default):</b></p> <table style="width: 100%; border-collapse: collapse; font-family: inherit; font-size: 13px; margin-bottom: 16px;"> <tbody> <tr><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-weight: 600; width: 35%;">General</td><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-family: monospace; font-size: 12px;">temp=1.0, topp=0.95, topk=20, minp=0, presencepenalty=1.5</td></tr> <tr><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-weight: 600;">Coding</td><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-family: monospace; font-size: 12px;">temp=0.6, topp=0.95, topk=20, minp=0, presencepenalty=0</td></tr> </tbody> </table> <p style="margin: 0 0 8px 0; font-size: 13px; color: #334155; line-height: 1.7;"><b>Non-thinking mode:</b></p> <table style="width: 100%; border-collapse: collapse; font-family: inherit; font-size: 13px;"> <tbody> <tr><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-weight: 600; width: 35%;">General</td><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-family: monospace; font-size: 12px;">temp=0.7, topp=0.8, topk=20, minp=0, presencepenalty=1.5</td></tr> <tr><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-weight: 600;">Reasoning</td><td style="padding: 6px 10px; border-bottom: 1px solid rgba(128,128,128,0.15); color: #334155; font-family: monospace; font-size: 12px;">temp=1.0, topp=1.0, topk=40, minp=0, presencepenalty=2.0</td></tr> </tbody> </table> <p style="margin: 16px 0 0 0; font-size: 12px; color: #64748b; line-height: 1.5;">Use <code style="background: #f1f5f9; padding: 2px 6px; border-radius: 4px; font-size: 11px;">--jinja</code> flag with llama.cpp. Thinking mode is on by default — disable with <code style="background: #f1f5f9; padding: 2px 6px; border-radius: 4px; font-size: 11px;">--chat-template-kwargs '{"enable_thinking":false}'</code>. Vision support requires mmproj file.</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, #4b5563 0%, #6b7280 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>📝</span> Usage </div> <div style="padding: 16px;"> <p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7;">Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.</p> <div style="background: #1e293b; border-radius: 8px; padding: 16px; margin-bottom: 12px;"> <pre style="margin: 0; font-family: 'SF Mono', 'Fira Code', monospace; font-size: 12px; color: #e2e8f0; line-height: 1.6; white-space: pre-wrap;"><span style="color: #94a3b8;"># Text only</span> llama-cli -m Qwen3.5-122B-A10B-Uncensored-APEX-Compact.gguf \ --jinja -c 131072 -ngl 99

<span style="color: #94a3b8;"># With vision</span> llama-cli -m Qwen3.5-122B-A10B-Uncensored-APEX-Compact.gguf \ --mmproj mmproj-Qwen3.5-122B-A10B-Uncensored-f16.gguf \ --jinja -c 131072 -ngl 99</pre> </div> <p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; line-height: 1.5;">For CPU inference: this 55 GB model fits in 64 GB+ RAM systems. For GPU offload, adjust <code style="background: #f1f5f9; padding: 2px 6px; border-radius: 4px; font-size: 11px;">-ngl</code> based on available VRAM.</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, #7c3aed 0%, #a855f7 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"> <span>🔗</span> Credits </div> <div style="padding: 16px;"> <p style="margin: 0; font-size: 13px; color: #334155; line-height: 1.7;"> <b>Base model:</b> <a href="https://huggingface.co/HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive" style="color: #c2410c; text-decoration: none;">HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive</a> (uncensored)<br> <b>Quantization:</b> <a href="https://github.com/mudler/apex-quant" style="color: #c2410c; text-decoration: none;">APEX — Adaptive Precision for EXpert Models</a> by <a href="https://github.com/mudler" style="color: #c2410c; text-decoration: none;">mudler</a> / <a href="https://github.com/mudler/LocalAI" style="color: #c2410c; text-decoration: none;">LocalAI</a> team<br> <b>Runtime:</b> Built on <a href="https://github.com/ggerganov/llama.cpp" style="color: #c2410c; text-decoration: none;">llama.cpp</a><br> <b>Original model:</b> <a href="https://huggingface.co/Qwen/Qwen3.5-122B-A10B" style="color: #c2410c; text-decoration: none;">Qwen/Qwen3.5-122B-A10B</a> </p> </div> </div> </div>