LLM EXPLORER 59,278 MODELS INDEXED

Ektome Qwen3.8 27B OQ6e MLX MTP by kvas-25

By kvas-25 · 242 downloads
HF Repo ↗ Copy URL

Ektome Qwen3.8 27B OQ6e MLX MTP is an open-source language model by kvas-25. Features: 27b LLM, VRAM: 23.6GB, License: apache-2.0, LLM Explorer Score: 0.32.

  6-bit   Abliterated Base model:quantized:zynerji/e... Base model:zynerji/ektome-qwen...   Conversational   Ektome   En   Mlx   Mtp   Multi-token-prediction   Omlx   Oq6e   Quantized   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vision
Model Card on HF 🤗: https://huggingface.co/kvas-25/Ektome-Qwen3.8-27B-oQ6e-MLX-MTP 

Ektome Qwen3.8 27B OQ6e MLX MTP Parameters and Internals

LLM NameEktome Qwen3.8 27B OQ6e MLX MTP
Repository 🤗https://huggingface.co/kvas-25/Ektome-Qwen3.8-27B-oQ6e-MLX-MTP 
Base Model(s)  Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored   Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored
Model Size27b
Required VRAM23.6 GB
Updated2026-08-22
Maintainerkvas-25
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   5.0 GB: 4-of-5   3.6 GB: 5-of-5
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ektome Qwen3.8 27B OQ6e MLX MTP

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.8 27B Escha W20K / 10.1 GB56197
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.5 27B0K / 55.2 GB811516
Note: green Score (e.g. "73.2") means that the model is better than kvas-25/Ektome-Qwen3.8-27B-oQ6e-MLX-MTP.