⚡ 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.
Gemma 4 26B-A4B Claude Opus Distill APEX GGUF
APEX (Adaptive Precision for EXpert Models) quantizations of gemma-4-26B-A4B-it-Claude-Opus-Distill — a Claude Opus reasoning-distilled version of google/gemma-4-26B-A4B-it by TeichAI.
Brought to you by the LocalAI team | APEX Project | Technical Report
Benchmark Results
Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF.
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: gemma-4-26B-A4B-it-Claude-Opus-Distill (same architecture as gemma-4-26B-A4B-it)
- Layers: 30
- Experts: 128 routed (8 active per token)
- Total Parameters: 26B
- Active Parameters: ~4B per token
- Vision: Built-in vision encoder (mmproj included)
- APEX Config: 5+5 symmetric edge gradient across 30 layers
- Calibration: v1.3 diverse dataset
Run with LocalAI
local-ai run mudler/gemma-4-26B-A4B-it-Claude-Opus-Distill-APEX-GGUF@gemma-4-26B-A4B-Claude-Distill-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.