LLM EXPLORER 65,418 MODELS INDEXED

Q36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT by oktayd

By oktayd · 196 downloads
HF Repo ↗ Copy URL

Q36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT is an open-source language model by oktayd. Features: 35b LLM, VRAM: 70.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

  Abliterated   Agent   Agentic   Agentic-coding Base model:finetune:huihui-ai/... Base model:huihui-ai/huihui-qw...   Claude-opus-4.7   Coding   Conversational Dataset:lambda/hermes-agent-re... Dataset:nousresearch/hermes-fu...   En   Endpoints compatible   Freetoken   Function-calling   Heretic   Hermes   Image-text-to-text   Lora   Mixture-of-experts   Moe   Mtp   Multimodal   Nextn   Nuclear   Obliteratus   Peft   Q36   Quantized   Qwen   Qwen3.6   Qwen3 5 moe   Reasoning   Reasoning-distillation   Refusal-reduction   Region:us   Safetensors   Sharded   Tensorflow   Tool-use   Uncensored   Unsloth   Vision   Vision-language   Vlm
Model Card on HF 🤗: https://huggingface.co/oktayd/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT 

Q36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT Parameters and Internals

LLM NameQ36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT
Repository 🤗https://huggingface.co/oktayd/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT 
Model Nameunsloth/Qwen3.6-35B-A3B
Base Model(s)  huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated   huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Model Size35b
Required VRAM70.4 GB
Updated2026-08-26
Maintaineroktayd
Model Typeqwen3_5_moe
Model Files  4.3 GB: 1-of-16   4.5 GB: 2-of-16   5.0 GB: 3-of-16   4.0 GB: 4-of-16   4.5 GB: 5-of-16   5.0 GB: 6-of-16   4.0 GB: 7-of-16   4.5 GB: 8-of-16   5.0 GB: 9-of-16   4.0 GB: 10-of-16   4.5 GB: 11-of-16   5.0 GB: 12-of-16   4.0 GB: 13-of-16   4.5 GB: 14-of-16   5.0 GB: 15-of-16   2.6 GB: 16-of-16   1.7 GB
Supported Languagesen
Quantization Typeq36
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Errorsreplace

Quantized Models of the Q36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT

Model
Likes
Downloads
VRAM
...ERATUS Hermes MTP Vision Llama14530 GB
...RATUS Hermes MTP Vision Ollama21100 GB

Best Alternatives to Q36 35B A3B Opus4.7 Ablit Heretic OBLITERATUS Hermes MTP Vision FT

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Qwen3.6 35B A3B MLX 4bit MTP0K / 20.5 GB8461
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 2Bit GSQ0K / 13.5 GB21197
Qwen3.6 35B A3B OQ4e Fp16 Mtp0K / 22.4 GB1871
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Note: green Score (e.g. "73.2") means that the model is better than oktayd/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT.