--- title: Qwen3.6-35B-A3B-APEX-GGUF canonical_url: "https://www.modelscope.cn/models/mudler/Qwen3.6-35B-A3B-APEX-GGUF" md_url: "https://www.modelscope.cn/models/mudler/Qwen3.6-35B-A3B-APEX-GGUF.md" repository: mudler/Qwen3.6-35B-A3B-APEX-GGUF last_updated: 2026-08-17 license: apache-2.0 base_model: - Qwen/Qwen3.6-35B-A3B base_model_relation: quantized library_name: - gguf - pytorch frameworks: - pytorch downloads: 16081 stars: 42 tags: - gguf - quantized - apex - moe - mixture-of-experts - qwen3 - vlm - vision --- # Qwen3.6-35B-A3B-APEX-GGUF > Qwen3.6-35B-A3B-APEX-GGUF - mudler 在 ModelScope 开源的模型。⚡ 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… mudler/Qwen3.6-35B-A3B-APEX-GGUF 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可，基于 Qwen/Qwen3.6-35B-A3B 构建。 - **Repository**: mudler/Qwen3.6-35B-A3B-APEX-GGUF - **License**: apache-2.0 - **Base model**: Qwen/Qwen3.6-35B-A3B - **Tags**: gguf, quantized, apex, moe, mixture-of-experts, qwen3, vlm, vision - **Downloads**: 16081 - **Stars**: 42 - **Last updated**: 2026-08-17 Source: https://www.modelscope.cn/models/mudler/Qwen3.6-35B-A3B-APEX-GGUF ---

⚡ 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.

# Qwen 3.6 35B-A3B APEX GGUF **APEX (Adaptive Precision for EXpert Models)** quantizations of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B). **Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team** | [APEX Project](https://github.com/mudler/apex-quant) | [Technical Report](https://github.com/mudler/apex-quant/blob/main/paper/APEX_Technical_Report.pdf) ## Benchmark Results All benchmarks run with llama.cpp b8797 on NVIDIA GB10 (122 GB VRAM). Perplexity and KL divergence measured on wikitext-2. HellaSwag zero-shot (400 tasks). KL divergence computed against BF16 reference logits. ### APEX vs Baselines (unsloth UD quants) | Model | Size | PPL ↓ | KL mean ↓ | KL median ↓ | KL max ↓ | HellaSwag ↑ | |-------|------|-------|-----------|-------------|----------|-------------| | BF16 (reference) | 65 GB | 6.722 | — | — | — | — | | Q8_0 | 35 GB | 6.720 | 0.0059 | 0.0022 | 9.72 | 82.5% | | UD-Q5_K_XL | 25 GB | 6.725 | 0.0083 | 0.0030 | 9.06 | 82.8% | | UD-Q5_K_S | 24 GB | 6.728 | 0.0095 | 0.0035 | 8.72 | 82.8% | | **APEX I-Balanced** | **24 GB** | **6.727** | **0.0103** | **0.0041** | **4.53** | **83.0%** | | APEX Balanced | 24 GB | 6.726 | 0.0117 | 0.0047 | 14.14 | 83.0% | | **APEX I-Quality** | **22 GB** | **6.735** | **0.0141** | **0.0054** | **5.69** | **82.5%** | | APEX Quality | 22 GB | 6.753 | 0.0155 | 0.0060 | 13.01 | 82.8% | | UD-Q4_K_XL | 21 GB | 6.735 | 0.0134 | 0.0050 | 5.14 | 82.3% | | UD-Q4_K_M | 21 GB | 6.736 | 0.0138 | 0.0054 | 7.86 | 83.3% | | **APEX I-Compact** | **17 GB** | **6.857** | **0.0451** | **0.0182** | **8.76** | **83.5%** | | APEX Compact | 17 GB | 6.862 | 0.0614 | 0.0261 | 17.58 | 83.3% | | UD-Q3_K_M | 16 GB | 6.883 | 0.0435 | 0.0163 | 9.37 | 82.8% | | **APEX I-Mini** | **14 GB** | **7.238** | **0.0999** | **0.0414** | **9.21** | **82.8%** | ![Complete Benchmark Summary](qwen36_summary.png) ![KL Max Comparison](qwen36_kl_max_bars.png) ![APEX vs Baselines](qwen36_apex_benchmarks.png) ### Highlights - **APEX I-Balanced (24 GB) achieves the lowest KL max (4.53) of any quant tested** — even lower than Q8_0 (9.72). The imatrix dramatically reduces worst-case divergence while matching UD-Q5_K_S on perplexity. - **At 17 GB**, APEX I-Compact beats UD-Q3_K_M (16 GB) on PPL (6.857 vs 6.883) and HellaSwag (83.5% vs 82.8%). - **imatrix consistently halves KL max**: I-Balanced 4.53 vs Balanced 14.14, I-Quality 5.69 vs Quality 13.01. - **APEX I-Mini (14 GB)** delivers usable quality (PPL 7.24, HellaSwag 82.8%) in the smallest package. ## Available Files | File | Profile | Size | Best For | |------|---------|------|----------| | Qwen3.6-35B-A3B-APEX-I-Balanced.gguf | I-Balanced | 24 GB | Best overall — lowest KL max of any quant | | Qwen3.6-35B-A3B-APEX-I-Quality.gguf | I-Quality | 22 GB | Highest quality with imatrix, 2 GB smaller | | Qwen3.6-35B-A3B-APEX-Quality.gguf | Quality | 22 GB | Highest quality standard | | Qwen3.6-35B-A3B-APEX-Balanced.gguf | Balanced | 24 GB | General purpose | | Qwen3.6-35B-A3B-APEX-I-Compact.gguf | I-Compact | 17 GB | Consumer GPUs, beats UD-Q3_K_M quality | | Qwen3.6-35B-A3B-APEX-Compact.gguf | Compact | 17 GB | Consumer GPUs | | Qwen3.6-35B-A3B-APEX-I-Mini.gguf | I-Mini | 14 GB | Smallest viable, fastest inference | | mmproj.gguf | Vision projector | ~1 GB | 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 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](https://github.com/mudler/apex-quant) for full details, technical report, and scripts. ## Architecture - **Model**: Qwen 3.6 35B-A3B (Qwen/Qwen3.6-35B-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) - **Vision**: Built-in vision encoder (mmproj included) - **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 ```bash local-ai run mudler/Qwen3.6-35B-A3B-APEX-GGUF@Qwen3.6-35B-A3B-APEX-I-Balanced.gguf ``` ## Credits APEX is brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. Developed through human-driven, AI-assisted research. Built on [llama.cpp](https://github.com/ggerganov/llama.cpp).