I host 30+ 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.
APEX (Adaptive Precision for EXpert Models) quantizations of InternScience/Agents-A1 — a 35B Mixture-of-Experts agentic model built to scale heterogeneous agentic abilities across long-horizon search, engineering, scientific research, instruction following, and tool calling.
Best overall — imatrix-enhanced, lowest worst-case divergence
Agents-A1-APEX-I-Quality.gguf
I-Quality
Highest quality with imatrix
Agents-A1-APEX-Quality.gguf
Quality
Highest quality (no imatrix)
Agents-A1-APEX-Balanced.gguf
Balanced
General purpose
Agents-A1-APEX-I-Compact.gguf
I-Compact
Consumer GPUs, imatrix-enhanced
Agents-A1-APEX-Compact.gguf
Compact
Consumer GPUs
Agents-A1-APEX-I-Mini.gguf
I-Mini
Smallest viable, fastest inference
mmproj.gguf
Vision projector
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 (first/last 5) 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 and keeping attention, SSM/Mamba, and shared-expert tensors at higher precision.
See the APEX project for full details, technical report, and scripts.
