mudler / Darwin-36B-Opus-APEX-GGUF

huggingface.co
Total runs: 3.4K
24-hour runs: -1.3K
7-day runs: -909
30-day runs: -1.8K
Model's Last Updated: August 17 2026

Introduction of Darwin-36B-Opus-APEX-GGUF

Model Details of Darwin-36B-Opus-APEX-GGUF

⚡ Each donation = another big MoE quantized

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.

🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors

💚 Big thanks to Hugging Face for generously donating additional storage — much appreciated.

Darwin-36B-Opus — APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of FINAL-Bench/Darwin-36B-Opus .

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

Available Files
File Profile Size Best For
Darwin-36B-Opus-APEX-I-Balanced.gguf I-Balanced 24 GB Best overall quality/size ratio
Darwin-36B-Opus-APEX-Balanced.gguf Balanced 24 GB General purpose
Darwin-36B-Opus-APEX-I-Quality.gguf I-Quality 22 GB Highest quality with imatrix
Darwin-36B-Opus-APEX-Quality.gguf Quality 22 GB Highest quality standard
Darwin-36B-Opus-APEX-I-Compact.gguf I-Compact 16 GB Consumer GPUs, best quality/size
Darwin-36B-Opus-APEX-Compact.gguf Compact 16 GB Consumer GPUs
Darwin-36B-Opus-APEX-I-Mini.gguf I-Mini 13 GB Smallest "safe" tier
Darwin-36B-Opus-APEX-I-Nano.gguf I-Nano 11 GB Experimental — IQ2_XXS mid-layer experts
Darwin-36B-Opus-F16.gguf F16 reference 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.

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
  • Calibration : v1.3 diverse dataset (chat, code, reasoning, multilingual, tool-calling, Wikipedia)
Run with LocalAI
local-ai run mudler/[email protected]
Credits

Runs of mudler Darwin-36B-Opus-APEX-GGUF on huggingface.co

3.4K
Total runs
-1.3K
24-hour runs
-1.3K
3-day runs
-909
7-day runs
-1.8K
30-day runs

More Information About Darwin-36B-Opus-APEX-GGUF huggingface.co Model

More Darwin-36B-Opus-APEX-GGUF license Visit here:

https://choosealicense.com/licenses/apache-2.0

Darwin-36B-Opus-APEX-GGUF huggingface.co

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 Url

https://huggingface.co/mudler/Darwin-36B-Opus-APEX-GGUF

mudler Darwin-36B-Opus-APEX-GGUF online free

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:

https://huggingface.co/mudler/Darwin-36B-Opus-APEX-GGUF

Darwin-36B-Opus-APEX-GGUF install

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:

https://huggingface.co/mudler/Darwin-36B-Opus-APEX-GGUF

Url of Darwin-36B-Opus-APEX-GGUF

Darwin-36B-Opus-APEX-GGUF huggingface.co Url

Provider of Darwin-36B-Opus-APEX-GGUF huggingface.co

mudler
ORGANIZATIONS

Other API from mudler

huggingface.co

Total runs: 1.1M
Run Growth: 413.9K
Growth Rate: 38.53%
Updated:June 22 2026