LLM EXPLORER 61,405 MODELS INDEXED

Qwen3.6 27B MTP Bf16 by mlx-community

By mlx-community · 1423 downloads

Qwen3.6 27B MTP Bf16 is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 0.8GB, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.6-27b   Bf16   Conversational   Draft-model   En   Mlx   Mlx-vlm   Mtp   Qwen   Qwen3.6   Qwen3.6-27b   Qwen3 5 mtp   Region:us   Safetensors   Speculative-decoding

Qwen3.6 27B MTP Bf16 Parameters and Internals

LLM NameQwen3.6 27B MTP Bf16
Repository πŸ€—https://huggingface.co/mlx-community/Qwen3.6-27B-MTP-bf16 
Base Model(s)  Qwen/Qwen3.6-27B   Qwen/Qwen3.6-27B
Model Size27b
Required VRAM0.8 GB
Updated2026-07-30
Maintainermlx-community
Model Typeqwen3_5_mtp
Model Files  0.8 GB
Supported Languagesen
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace