Back to Models
mudler logo

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

mudlergeneral

⚡ 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.

Carnice Qwen3.6 MoE 35B-A3B APEX GGUF

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

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

Available Files

FileProfileSizeBest For
Carnice-Qwen3.6-MoE-35B-A3B-APEX-I-Balanced.ggufI-Balanced24 GBBest overall quality/size ratio
Carnice-Qwen3.6-MoE-35B-A3B-APEX-I-Quality.ggufI-Quality22 GBHighest quality with imatrix
Carnice-Qwen3.6-MoE-35B-A3B-APEX-Quality.ggufQuality22 GBHighest quality standard
Carnice-Qwen3.6-MoE-35B-A3B-APEX-Balanced.ggufBalanced24 GBGeneral purpose
Carnice-Qwen3.6-MoE-35B-A3B-APEX-I-Compact.ggufI-Compact17 GBConsumer GPUs, best quality/size
Carnice-Qwen3.6-MoE-35B-A3B-APEX-Compact.ggufCompact17 GBConsumer GPUs
Carnice-Qwen3.6-MoE-35B-A3B-APEX-I-Mini.ggufI-Mini14 GBSmallest viable, fastest inference

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).

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

Architecture

  • Model: Carnice Qwen3.6 MoE 35B-A3B (fine-tuned for agentic/tool-calling)
  • 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)
  • 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/Carnice-Qwen3.6-MoE-35B-A3B-APEX-GGUF@Carnice-Qwen3.6-MoE-35B-A3B-APEX-I-Balanced.gguf

Credits

Visit Website

0 reviews

5
0
4
0
3
0
2
0
1
0
Likes13
Downloads
📝

No reviews yet

Be the first to review mudler/Carnice-Qwen3.6-MoE-35B-A3B-APEX-GGUF!

Model Info

Providermudler
Categorygeneral
Reviews0
Avg. Rating / 5.0

Community

Likes13
Downloads

Rating Guidelines

★★★★★Exceptional
★★★★Great
★★★Good
★★Fair
Poor