mudler/Qwen3.6-35B-A3B-APEX-GGUF

<!-- apex-banner-v2 --> <div style="background-color: #f59e0b; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;"> <h2 style="color: white; margin: 0 0 10px 0;">⚡ Each donation = another big MoE quantized</h2> <p style="font-size: 18px; margin: 0 0 15px 0;">I host <b>25+ free APEX MoE quantizations</b> as independent research. My only local hardware is an <b>NVIDIA DGX Spark</b> (122 GB unified memory), enough for ~30-50B-class MoEs, but <b>bigger ones (200B+) require rented compute</b> on H100/H200/Blackwell, typically $20-100 per quant.<br>If APEX quants are useful to you, your support directly funds those bigger runs.</p> <p style="font-size: 20px; margin: 0;"> <a href="https://www.patreon.com/cw/mudler" style="color: white; text-decoration: underline;">🎉 Patreon (Monthly)</a> &nbsp;|&nbsp; <a href="https://www.buymeacoffee.com/mudler" style="color: white; text-decoration: underline;">☕ Buy Me a Coffee</a> &nbsp;|&nbsp; <a href="https://github.com/sponsors/mudler" style="color: white; text-decoration: underline;">⭐ GitHub Sponsors</a> </p> <p style="font-size: 14px; margin: 10px 0 0 0; opacity: 0.9;">💚 Big thanks to Hugging Face for generously donating additional storage, much appreciated.</p> </div>

Qwen 3.6 35B-A3B APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of Qwen/Qwen3.6-35B-A3B.

Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team | APEX Project | Technical Report

Benchmark Results

All benchmarks run with llama.cpp b8797 on NVIDIA GB10 (122 GB VRAM). Perplexity and KL divergence measured on wikitext-2. HellaSwag zero-shot (400 tasks). KL divergence computed against BF16 reference logits.

APEX vs Baselines (unsloth UD quants)

[image]

[image]

[image]

Highlights

• —APEX I-Balanced (24 GB) achieves the lowest KL max (4.53) of any quant tested — even lower than Q80 (9.72). The imatrix dramatically reduces worst-case divergence while matching UD-Q5K_S on perplexity.
• —At 17 GB, APEX I-Compact beats UD-Q3KM (16 GB) on PPL (6.857 vs 6.883) and HellaSwag (83.5% vs 82.8%).
• —imatrix consistently halves KL max: I-Balanced 4.53 vs Balanced 14.14, I-Quality 5.69 vs Quality 13.01.
• —APEX I-Mini (14 GB) delivers usable quality (PPL 7.24, HellaSwag 82.8%) in the smallest package.

Available Files

What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient — edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

The key insight: in MoE models, expert FFN tensors make up the bulk of model weight but only ~8/256 experts activate per token. APEX compresses middle-layer experts more aggressively while preserving edge layers (first/last 5) and keeping attention, SSM/Mamba, and shared expert tensors at higher precision.

See the APEX project for full details, technical report, and scripts.

Architecture

• —Model: Qwen 3.6 35B-A3B (Qwen/Qwen3.6-35B-A3B)
• —Layers: 40
• —Experts: 256 routed + shared (8 active per token)
• —Total Parameters: ~35B
• —Active Parameters: ~3B per token
• —Attention: Hybrid (full attention every 4th layer, linear/Mamba otherwise)
• —Vision: Built-in vision encoder (mmproj included)
• —APEX Config: 5+5 symmetric edge gradient across 40 layers
• —Calibration: v1.3 diverse dataset (chat, code, reasoning, multilingual, tool-calling, Wikipedia)
• —llama.cpp: Built with b8797

Run with LocalAI

local-ai run mudler/Qwen3.6-35B-A3B-APEX-GGUF@Qwen3.6-35B-A3B-APEX-I-Balanced.gguf

Credits

APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.