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

⚡ Each donation = another big MoE quantized

I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.
If APEX quants are useful to you, your support directly funds those bigger runs.

🎉 Patreon (Monthly)  |  ☕ Buy Me a Coffee  |  ⭐ GitHub Sponsors

💚 Big thanks to Hugging Face for generously donating additional storage — much appreciated.

Qwen3.6 35B-A3B Uncensored Heretic APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic.

Brought to you by the LocalAI team | APEX Project | Technical Report

Available Files

File	Profile	Size	Best For
Qwen3.6-35B-A3B-uncensored-heretic-APEX-I-Balanced.gguf	I-Balanced	24 GB	Best overall quality/size ratio
Qwen3.6-35B-A3B-uncensored-heretic-APEX-Balanced.gguf	Balanced	24 GB	General purpose
Qwen3.6-35B-A3B-uncensored-heretic-APEX-I-Quality.gguf	I-Quality	22 GB	Highest quality with imatrix
Qwen3.6-35B-A3B-uncensored-heretic-APEX-Quality.gguf	Quality	22 GB	Highest quality standard
Qwen3.6-35B-A3B-uncensored-heretic-APEX-I-Compact.gguf	I-Compact	17 GB	Consumer GPUs, best quality/size
Qwen3.6-35B-A3B-uncensored-heretic-APEX-Compact.gguf	Compact	17 GB	Consumer GPUs
Qwen3.6-35B-A3B-uncensored-heretic-APEX-I-Mini.gguf	I-Mini	14 GB	Smallest viable, fastest inference
mmproj.gguf	Vision projector	~1 GB	Required for image understanding

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: Qwen3.6 35B-A3B Uncensored Heretic (uncensored fine-tune)
• Base: Qwen 3.6 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)

Run with LocalAI

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

Credits

• Heretic uncensored fine-tune: llmfan46
• APEX quantization: LocalAI team
• Built on llama.cpp