中文Sign up

mudler/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-GGUF

🤗 Hugging Face sourceapache-2.03B activated216 GBGGUF✓ 8 checksumsupdated today
Needs seeder →

⚡ 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 — Claude 4.6 Opus Reasoning Distilled — APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled.

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

Available Files

File Profile Size Best For
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Balanced.gguf I-Balanced 24 GB Best overall quality/size ratio
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-Balanced.gguf Balanced 24 GB General purpose
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Quality.gguf I-Quality 21 GB Highest quality with imatrix
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-Quality.gguf Quality 21 GB Highest quality standard
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Compact.gguf I-Compact 16 GB Consumer GPUs, best quality/size
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-Compact.gguf Compact 16 GB Consumer GPUs
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Mini.gguf I-Mini 13 GB Smallest viable, fastest inference
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-F16.gguf F16 65 GB Full precision reference

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 Claude 4.6 Opus Reasoning Distilled (reasoning 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)
  • Modality: Text only (no vision encoder in upstream)
  • 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-Claude-4.6-Opus-Reasoning-Distilled-APEX-GGUF@Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-APEX-I-Balanced.gguf

Credits