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 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.
Nano (experimental tier)
The
APEX Nano
tier pushes mid-layer routed experts to
IQ2_XXS (2.06 bpw)
, near-edge to IQ2_S, edges to Q3_K, with shared experts kept at Q5_K. About 20% smaller than Mini with modest quality cost — viable only on MoE thanks to sparse per-token expert activation. Requires imatrix.
Benchmarks pending. Feedback welcome.
Architecture
Base
: Qwen 3.5 MoE (Qwen3_5MoeForCausalLM) — evolutionary-merge reasoning fine-tune
Layers
: 40
Experts
: 256 routed (8 active per token)
Total Parameters
: ~36B
Active Parameters
: ~3B per token
Hidden size
: 2048
Attention
: Hybrid (full attention every 4th layer, linear/Mamba otherwise)
APEX Config
: 5+5 symmetric edge gradient across 40 layers
Darwin-36B-Opus-APEX-GGUF huggingface.co is an AI model on huggingface.co that provides Darwin-36B-Opus-APEX-GGUF's model effect (), which can be used instantly with this mudler Darwin-36B-Opus-APEX-GGUF model. huggingface.co supports a free trial of the Darwin-36B-Opus-APEX-GGUF model, and also provides paid use of the Darwin-36B-Opus-APEX-GGUF. Support call Darwin-36B-Opus-APEX-GGUF model through api, including Node.js, Python, http.
Darwin-36B-Opus-APEX-GGUF huggingface.co is an online trial and call api platform, which integrates Darwin-36B-Opus-APEX-GGUF's modeling effects, including api services, and provides a free online trial of Darwin-36B-Opus-APEX-GGUF, you can try Darwin-36B-Opus-APEX-GGUF online for free by clicking the link below.
mudler Darwin-36B-Opus-APEX-GGUF online free url in huggingface.co:
Darwin-36B-Opus-APEX-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Darwin-36B-Opus-APEX-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Darwin-36B-Opus-APEX-GGUF install, users can directly use Darwin-36B-Opus-APEX-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Darwin-36B-Opus-APEX-GGUF install url in huggingface.co: