SC117/Agents-A1-Uncensored-MTP-APEX-GGUF overview

---

library_name: transformers

license: apache-2.0

license_link: https://huggingface.co/InternScience/Agents-A1/blob/main/LICENSE

pipeline_tag: text-generation

tags:

• qwen3_5_moe
• qwen3_5
• reasoning
• agentic
• uncensored
• mtp
• apex
• quantization
• gguf
• multimodal

base_model:

• InternScience/Agents-A1

---

<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: #bbf7d0; border-radius: 50%;"></div>

<div style="position: absolute; bottom: -20px; left: 40px; width: 80px; height: 80px; background: #86efac; border-radius: 50%;"></div>

<div style="position: absolute; top: 50%; left: -15px; width: 60px; height: 60px; background: #bbf7d0; border-radius: 50%;"></div>

<div style="display: inline-flex; gap: 8px; margin-bottom: 16px; position: relative; z-index: 1;">

<span style="background: #10b981; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">APEX</span>

<span style="background: #6366f1; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">MTP</span>

<span style="background: #0ea5e9; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">Vision</span>

<span style="background: #f97316; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">Apache-2.0</span>

</div>

<h1 style="margin: 0 0 8px 0; font-size: 32px; font-weight: 700; color: #064e3b; letter-spacing: -0.5px; border: none; position: relative; z-index: 1;">Agents-A1-Uncensored-MTP-APEX</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/Agents-A1-Uncensored-MTP-APEX-GGUF/blob/main/README_zh.md" style="color: #10b981; text-decoration: none;">📖 中文文档</a></p>

<p style="margin: 0; font-size: 15px; color: #6b7280; position: relative; z-index: 1;">Uncensored 35B agentic MoE · APEX-quantized GGUFs + MTP + BF16 mmproj</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, #10b981 0%, #059669 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🤖</span> About Agents-A1</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/InternScience/Agents-A1" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">Agents-A1</a> is a 35B-parameter Mixture-of-Experts <b>agentic model</b> from <a href="https://huggingface.co/InternScience" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">InternScience</a>, post-trained on top of <a href="https://huggingface.co/Qwen/Qwen3.5-35B-A3B" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">Qwen3.5-35B-A3B</a> via a three-stage paradigm: full-domain SFT → domain-level teacher training → multi-teacher multi-domain on-policy distillation.</p>

<p style="margin: 0 0 12px 0;">Despite operating in the ~35B model class, Agents-A1 delivers highly competitive performance against frontier-scale systems such as GPT-5.5, DeepSeek-V4-pro, and Kimi-K2.6 — achieving SOTA on Seal-0 (56.4), HiPhO (46.4), FrontierScience-Olympiad (79.0), IFBench (80.6), IFEval (94.8), and best-among-comparable on BrowseComp (75.5), XBench-DS-2510 (86.0), GAIA (96.0), SciCode (44.3), HLE (47.6), and MolBench-bind (56.8).</p>

<p style="margin: 0;">This GGUF package includes the <b>mmproj-Agents-A1-Uncensored-MTP-BF16.gguf</b> vision projector for multimodal (image + text) capabilities with llama.cpp. MTP layers are extracted from <a href="https://huggingface.co/Qwen/Qwen3.5-35B-A3B" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">Qwen3.5-35B-A3B</a> and injected into Agents-A1's safetensors (see <b>MTP Extraction &amp; Injection</b> section). <b>License: Apache-2.0.</b></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 Adaptation</div>

<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">

<p style="margin: 0 0 12px 0;">This release merges the selected behavior-modification LoRA into the BF16 base before MTP injection and APEX quantization. The uncensored adaptation was produced with <a href="https://github.com/wuwangzhang1216/abliterix" target="_blank" style="color: #c2410c; text-decoration: none; font-weight: 700;">abliterix</a>. It is intended to reduce refusal behavior and can produce responses that differ materially from the original model.</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;">Evaluation result</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">2 refusals / 100 prompts</td></tr><tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">KL divergence</td><td style="padding: 6px 10px; color: #4b5563; background: white;">0.016058</td></tr></tbody></table>

<p style="margin: 12px 0 0 0; font-size: 12px; color: #9a3412;">Use responsibly: evaluate the model for your deployment context and apply appropriate safeguards.</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, #10b981 0%, #059669 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;">Qwen3.5 MoE (Mixture of Experts)</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;">35B total, 3B active per 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;">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 experts, 8 active per 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;">40 transformer layers + 1 MTP layer</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;">262,144 tokens</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;">MTP Source</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Qwen3.5-35B-A3B (1 layer, 785 tensors, injected)</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;">Block Count</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">41 (blk.0–39 + blk.40 MTP)</td></tr>

<tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">License</td><td style="padding: 6px 10px; color: #4b5563; background: white;">Apache-2.0</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, #10b981 0%, #059669 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🔧</span> MTP Extraction &amp; Injection</div>

<div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;">

<p style="margin: 0 0 12px 0;">The released <a href="https://huggingface.co/InternScience/Agents-A1" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">InternScience/Agents-A1</a> checkpoint is a <b>40-layer Qwen3.5-35B-A3B MoE</b> without MTP (Multi-Token Prediction) layers. To enable MTP acceleration in llama.cpp (which speeds up long-context generation by 10–30%), we <b>extract the 1 MTP layer from Qwen3.5-35B-A3B</b> and inject it into Agents-A1's safetensors before GGUF conversion.</p>

<p style="margin: 0 0 12px 0;">The full pipeline has 4 steps: (1) Extract 785 MTP tensors from <code>Qwen3.5-35B-A3B</code> (filter keys containing "mtp"); (2) append as a new shard <code>model-15-of-15.safetensors</code> and update <code>model.safetensors.index.json</code>'s <code>metadata.total_size</code> and <code>weight_map</code> (do not modify the original 14 shards); (3) convert to BF16 GGUF via the master-branch llama.cpp <code>convert_hf_to_gguf.py</code> — the master build auto-detects <b>regular layers blk.0–39</b> + <b>MTP layer blk.40.nextn.</b> (785 tensors); (4) quantize with APEX llama-quantize using <code>qwen36_35b_mtp_.txt</code> configs which already include the blk.40 override (MTP kept at <b>Q8_0</b> across all tiers — no manual patching needed). The imatrix <code>Qwen3.5-35B-A3B.imatrix.gguf</code> is reused directly (same architecture, compatible weights).</p>

<p style="margin: 0 0 8px 0; font-weight: bold; color: #064e3b;">Reproduction command (example: I-Compact tier)</p>

<pre style="margin: 0; font-family: monospace; background: #f8fafc; padding: 10px 14px; border-radius: 6px; border: 1px solid #e2e8f0; font-size: 12px; color: #1e293b; white-space: pre;">F:\llama.cpp\...\llama-quantize.exe ^

--imatrix J:\Models\Qwen3.5-35B-A3B.imatrix.gguf ^

--tensor-type-file E:\apex-quant\configs\qwen36_35b_mtp_compact.txt ^

J:\Models\Agents-A1-Uncensored-MTP-GGUF\Agents-A1-Uncensored-MTP-BF16.gguf ^

J:\Models\Agents-A1-Uncensored-MTP-APEX-GGUF\Agents-A1-Uncensored-MTP-APEX-I-Compact.gguf ^

Q4_K_M</pre>

</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, #10b981 0%, #059669 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📊</span> BenchLocal Results (APEX-I-Compact, 16.14 GB)</div>

<div style="padding: 16px;">

<table style="width: 100%; border-collapse: collapse; font-size: 13px;"><thead><tr style="background: rgba(16,185,129,0.05);"><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">Mode</th><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">ToolCall-15</th><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">BugFind-15</th><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">HermesAgent-20</th><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">Max</th><th style="padding: 7px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold;">Eff.</th></tr></thead><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;">Thinking</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">100</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">88</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">87</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #047857; background: white;">91.2</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">71.2</td></tr>

<tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">No Thinking</td><td style="padding: 6px 10px; color: #334155; background: white;">97</td><td style="padding: 6px 10px; color: #334155; background: white;">100</td><td style="padding: 6px 10px; color: #334155; background: white;">85</td><td style="padding: 6px 10px; font-weight: bold; color: #047857; background: white;">93.1</td><td style="padding: 6px 10px; color: #334155; background: white;">57.1</td></tr>

</tbody></table>

<p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; font-style: italic;">RTX 5070 Ti 16GB + 128GB RAM · No-thinking mode achieves higher ceiling (BugFind +12) but suffers more retries on complex agent scenarios.</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, #10b981 0%, #059669 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; font-size: 13px; color: #334155; line-height: 1.7;">

<p style="margin: 0 0 8px 0; font-weight: bold; color: #064e3b;">llama.cpp (text only)</p>

<pre style="margin: 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;">hf download SC117/Agents-A1-Uncensored-MTP-APEX-GGUF --include "*.gguf" --local-dir ./models

./llama-server -m ./models/Agents-A1-Uncensored-MTP-APEX-I-Compact.gguf -ngl 99 -c 131072</pre>

<p style="margin: 0 0 8px 0; font-weight: bold; color: #064e3b;">llama.cpp (vision + text)</p>

<pre style="margin: 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 ./models/Agents-A1-Uncensored-MTP-APEX-I-Compact.gguf --mmproj ./models/mmproj-Agents-A1-Uncensored-MTP-BF16.gguf -ngl 99 -c 131072</pre>

<p style="margin: 0 0 8px 0; font-weight: bold; color: #064e3b;">vLLM</p>

<pre style="margin: 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;">vllm serve SC117/Agents-A1-Uncensored-MTP-APEX-GGUF --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3

·

Tool-call variant

vllm serve SC117/Agents-A1-Uncensored-MTP-APEX-GGUF --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder</pre>

<p style="margin: 0 0 8px 0; font-weight: bold; color: #064e3b;">SGLang</p>

<pre style="margin: 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;">python3 -m sglang.launch_server --model-path "SC117/Agents-A1-Uncensored-MTP-APEX-GGUF" --host 0.0.0.0 --port 30000</pre>

</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, #10b981 0%, #059669 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🎛️</span> Recommended Sampling Parameters</div>

<div style="padding: 16px;">

<p style="margin: 0 0 12px 0; font-size: 13px; color: #334155;">From the <a href="https://huggingface.co/InternScience/Agents-A1#recommended-sampling-parameters" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">official Agents-A1 model card</a>:</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;">temperature</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;">0.85</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;">top_p</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;">0.95</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;">top_k</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;">20</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;">min_p</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;">0.0</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;">presence_penalty</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;">1.1</td></tr>

<tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">repetition_penalty</td><td style="padding: 6px 10px; color: #4b5563; font-family: monospace; background: white;">1.0</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, #10b981 0%, #059669 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;">

<p style="margin: 0 0 12px 0; font-size: 13px; color: #334155; line-height: 1.7;">These GGUF files are quantized using <a href="https://github.com/mudler/apex-quant" target="_blank" style="color: #047857; text-decoration: none; font-weight: 700;">APEX</a>, an MoE-aware mixed-precision quantization technique. APEX classifies every tensor by its role — routed expert, shared expert, SSM, or attention — and applies a layer-wise precision gradient, giving sensitive edge layers (including the MTP layer) higher precision and compressing redundant middle layers more aggressively.</p>

<p style="margin: 0; font-size: 13px; color: #334155; line-height: 1.7; font-weight: 700;">APEX beats Q8_0 perplexity at half the size — and even beats F16 in some cases.</p>

<p style="margin: 12px 0 0 0; font-size: 13px; color: #334155;">The <code>qwen36_35b_mtp_*.txt</code> configs include overrides for <b>blk.40</b> (the MTP layer), preserving it at Q8_0 across all four I- tiers. The same <code>Qwen3.5-35B-A3B.imatrix.gguf</code> is reused (same architecture, compatible MoE expert layout).</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, #10b981 0%, #059669 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(16,185,129,0.05);"><th style="padding: 8px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold; width: 35%;">File</th><th style="padding: 8px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold; width: 15%;">Size</th><th style="padding: 8px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold; width: 15%;">Profile</th><th style="padding: 8px 10px; border-bottom: 2px solid #10b981; text-align: left; color: #047857; font-weight: bold; width: 35%;">Best For</th></tr></thead><tbody>

<tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;"><code>*-APEX-I-Quality.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">21.75 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">I-Quality</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">High quality (Q6_K + iq4_xs attention)</td></tr>

<tr><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;"><code>*-APEX-I-Balanced.gguf</code></td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">24.21 GB</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">I-Balanced</td><td style="padding: 8px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #334155; background: white;">Best all-rounder (Q6_K + Q5_K experts)</td></tr>

<tr><td style="padding: 8px 10px; color: #334155;"><code>*-APEX-I-Compact.gguf</code></td><td style="padding: 8px 10px; color: #334155;">16.14 GB</td><td style="padding: 8px 10px; color: #334155;">I-Compact</td><td style="padding: 8px 10px; color: #334155;">Best quality/size ratio (Q4_K default)</td></tr>

<tr><td style="padding: 8px 10px; color: #334155;"><code>*-APEX-I-Mini.gguf</code></td><td style="padding: 8px 10px; color: #334155;">13.36 GB</td><td style="padding: 8px 10px; color: #334155;">I-Mini</td><td style="padding: 8px 10px; color: #334155;">Most compact, fits in 16GB VRAM (Q3_K + iq2_s)</td></tr>

</tbody></table>

<p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b; font-style: italic;">BF16 source: <code>Agents-A1-Uncensored-MTP-BF16.gguf</code> (66.19 GB). imatrix: <code>Qwen3.5-35B-A3B.imatrix.gguf</code> (reused from base model).</p>

</div>

</div>

</div>

Links

• Original Model: https://huggingface.co/InternScience/Agents-A1
• Base Model (MTP source): https://huggingface.co/Qwen/Qwen3.5-35B-A3B
• Paper: https://arxiv.org/abs/2606.30616
• APEX Quantization: https://github.com/mudler/apex-quant
• abliterix (Uncensored adaptation): https://github.com/wuwangzhang1216/abliterix
• BenchLocal Results: https://scorp1o117.github.io/benchlocal-results/

Citation

@misc{bai2026scalinghorizonparametersreaching,
      title={Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent},
      author={Lei Bai and Zongsheng Cao and Yang Chen and Zhiyao Cui and Shangheng Du and Yue Fan and Shiyang Feng and Zijie Guo and Haonan He and Liang He and Xiaohan He and Shuyue Hu and Yusong Hu and Songtao Huang and Yichen Jiang and Hao Li and Xin Li and Dahua Lin and Weihao Lin and Fenghua Ling and Dongrui Liu and Zhuo Liu and Runmin Ma and Chunjiang Mu and others},
      year={2026},
      eprint={2606.30616},
      archivePrefix={arXiv}
}