LLM EXPLORER 62,857 MODELS INDEXED

Qwen3.6 35B A3B Heretic NVFP4 by AEON-7

By AEON-7 · 228606 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B Heretic NVFP4 is an open-source language model by AEON-7. Features: 35b LLM, VRAM: 23.4GB, License: apache-2.0, LLM Explorer Score: 0.34.

  1m-context   35b   3b-active   4-bit   8-bit   Aarch64   Abliterated   Aeon   Aeon-7   Agentic   Arm64 Base model:quantized:tvall43/q... Base model:tvall43/qwen3.6-35b...   Blackwell   Chat   Chunked-prefill   Coding   Compressed-tensors   Conversational   Decensored   Dflash   Dgx-spark   En   Endpoints compatible   English   Flashinfer-cutlass   Fp4   Fp8-kv-cache   Function-calling   Gated-deltanet   Gb10   Gdn   Gpu   Grace-blackwell   Heretic   Hybrid   Hybrid-attention   Image-text-to-text   Instruct   Linear-attention   Llmcompressor   Long-context   Mixture-of-experts   Moe   Multimodal   Native-fp4   Nvfp4   Openai-api   Openai-compatible   Prefix-caching   Production-ready   Quantized   Qwen   Qwen3   Qwen3.5   Qwen3.6   Qwen3 5 moe   Reasoning   Refusal-removed   Region:us   Safetensors   Sm 121a   Sparse   Sparse-moe   Speculative-decoding   Thinking   Tool-calling   Uncensored   Unfiltered   Vision   Vision-language   Vllm   Weight-quantization
Model Card on HF 🤗: https://huggingface.co/AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4 

Qwen3.6 35B A3B Heretic NVFP4 Parameters and Internals

LLM NameQwen3.6 35B A3B Heretic NVFP4
Repository 🤗https://huggingface.co/AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4 
Base Model(s)  tvall43/Qwen3.6-35B-A3B-heretic   tvall43/Qwen3.6-35B-A3B-heretic
Model Size35b
Required VRAM23.4 GB
Updated2026-10-03
MaintainerAEON-7
Model Typeqwen3_5_moe
Model Files  23.4 GB
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.4
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B Heretic NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB1141
Qwen3.6 35B A3B NPU2256K /  GB1080
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1506004506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4.